{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/sota/semantic-segmentation-on-ade20k","task":{"name":"Semantic Segmentation","url":"/task/semantic-segmentation","note":null},"dataset":{"name":"ADE20K","url":"/dataset/ade20k"},"category":"Computer Vision","categories":["Computer Code","Computer Vision","Medical","Robots"],"category_note":null,"description":null,"description_from":null,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["Validation mIoU","Test Score","Params (M)","GFLOPs (512 x 512)","GFLOPs","Mean IoU (class)"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction; the tokens 'score' and 'time' are not used on this page); null = not inferred, chart draws points only","by_metric":{"Validation mIoU":null,"Test Score":null,"Params (M)":"lower","GFLOPs (512 x 512)":null,"GFLOPs":null,"Mean IoU (class)":"higher"}},"counts":{"rows":235,"rows_with_code":226,"rows_with_paper_page":235,"rows_dated":235,"rows_using_additional_data":18},"rows":[{"rank_in_archive_order":1,"model":"ViT-P (InternImage-H)","metrics":{"Params (M)":"1610","Validation mIoU":"63.6"},"uses_additional_data":true,"paper_date":"2025-05-26","paper":"/paper/the-missing-point-in-vision-transformers-for","paper_url":"https://arxiv.org/abs/2505.19795v1","paper_title":"The Missing Point in Vision Transformers for Universal Image Segmentation","code":"https://github.com/sajjad-sh33/vit-p","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":2,"model":"ONE-PEACE","metrics":{"Params (M)":"1500","Validation mIoU":"63.0"},"uses_additional_data":true,"paper_date":"2023-05-18","paper":"/paper/one-peace-exploring-one-general","paper_url":"https://arxiv.org/abs/2305.11172v1","paper_title":"ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities","code":"https://github.com/modelscope/modelscope","n_code_links":2,"official":{"repos":["OFA-Sys/ONE-PEACE"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":5,"n_constructed":2,"n_ran_checked":4,"n_instrument":1,"n_unverified":2,"n_samples":7,"n_pointer_only_licence":1,"sample_list":"/paper/one-peace-exploring-one-general#ran","syntology_url":"https://syntology.ai/paper/2305.11172","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.11172"}}}},{"rank_in_archive_order":3,"model":"InternImage-H","metrics":{"GFLOPs":"4635","Params (M)":"1310","Validation mIoU":"62.9"},"uses_additional_data":true,"paper_date":"2022-11-10","paper":"/paper/internimage-exploring-large-scale-vision","paper_url":"https://arxiv.org/abs/2211.05778v4","paper_title":"InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions","code":"https://github.com/opengvlab/internimage","n_code_links":3,"official":{"repos":["opengvlab/internimage"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["listed"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":0,"sample_list":"/paper/internimage-exploring-large-scale-vision#ran","syntology_url":"https://syntology.ai/paper/2211.05778","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.05778"}}}},{"rank_in_archive_order":4,"model":"M3I Pre-training (InternImage-H)","metrics":{"Params (M)":"1310","Validation mIoU":"62.9"},"uses_additional_data":true,"paper_date":"2022-11-17","paper":"/paper/towards-all-in-one-pre-training-via","paper_url":"https://arxiv.org/abs/2211.09807v2","paper_title":"Towards All-in-one Pre-training via Maximizing Multi-modal Mutual Information","code":"https://github.com/OpenGVLab/M3I-Pretraining","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":5,"model":"BEiT-3","metrics":{"Params (M)":"1900","Validation mIoU":"62.8"},"uses_additional_data":true,"paper_date":"2022-08-22","paper":"/paper/image-as-a-foreign-language-beit-pretraining","paper_url":"https://arxiv.org/abs/2208.10442v2","paper_title":"Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks","code":"https://github.com/microsoft/unilm/tree/master/beit","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":6,"model":"EVA","metrics":{"Params (M)":"1074","Validation mIoU":"62.3"},"uses_additional_data":true,"paper_date":"2022-11-14","paper":"/paper/eva-exploring-the-limits-of-masked-visual","paper_url":"https://arxiv.org/abs/2211.07636v2","paper_title":"EVA: Exploring the Limits of Masked Visual Representation Learning at Scale","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":6,"official":{"repos":["baaivision/eva","rwightman/pytorch-image-models"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":0,"sample_list":"/paper/eva-exploring-the-limits-of-masked-visual#ran","syntology_url":"https://syntology.ai/paper/2211.07636","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.07636"}}}},{"rank_in_archive_order":7,"model":"ViT-P (OneFormer, InternImage-H)","metrics":{"Params (M)":"1400","Validation mIoU":"61.6"},"uses_additional_data":false,"paper_date":"2025-05-26","paper":"/paper/the-missing-point-in-vision-transformers-for","paper_url":"https://arxiv.org/abs/2505.19795v1","paper_title":"The Missing Point in Vision Transformers for Universal Image Segmentation","code":"https://github.com/sajjad-sh33/vit-p","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":8,"model":"ViT-Adapter-L (Mask2Former, BEiTv2 pretrain)","metrics":{"Params (M)":"571","Validation mIoU":"61.5"},"uses_additional_data":true,"paper_date":"2022-05-17","paper":"/paper/vision-transformer-adapter-for-dense","paper_url":"https://arxiv.org/abs/2205.08534v4","paper_title":"Vision Transformer Adapter for Dense Predictions","code":"https://github.com/czczup/vit-adapter","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":9,"model":"FD-SwinV2-G","metrics":{"Params (M)":"3000","Validation mIoU":"61.4"},"uses_additional_data":false,"paper_date":"2022-05-27","paper":"/paper/contrastive-learning-rivals-masked-image","paper_url":"https://arxiv.org/abs/2205.14141v3","paper_title":"Contrastive Learning Rivals Masked Image Modeling in Fine-tuning via Feature Distillation","code":"https://github.com/SwinTransformer/Feature-Distillation","n_code_links":1,"official":{"repos":["SwinTransformer/Feature-Distillation"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":5,"ran_from_kinds":["official"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":5,"n_samples":8,"n_pointer_only_licence":8,"sample_list":"/paper/contrastive-learning-rivals-masked-image#ran","syntology_url":"https://syntology.ai/paper/2205.14141","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.14141"}}}},{"rank_in_archive_order":10,"model":"RevCol-H (Mask2Former)","metrics":{"Params (M)":"2439","Validation mIoU":"61.0"},"uses_additional_data":true,"paper_date":"2022-12-22","paper":"/paper/reversible-column-networks","paper_url":"https://arxiv.org/abs/2212.11696v3","paper_title":"Reversible Column Networks","code":"https://github.com/megvii-research/revcol","n_code_links":1,"official":{"repos":["megvii-research/revcol"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":8,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]},"syntology":{"n_ran":8,"n_constructed":8,"n_ran_checked":8,"n_instrument":0,"n_unverified":3,"n_samples":11,"n_pointer_only_licence":0,"sample_list":"/paper/reversible-column-networks#ran","syntology_url":"https://syntology.ai/paper/2212.11696","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.11696"}}}},{"rank_in_archive_order":11,"model":"MasK DINO (SwinL, multi-scale)","metrics":{"Params (M)":"223","Validation mIoU":"60.8"},"uses_additional_data":true,"paper_date":"2022-06-06","paper":"/paper/mask-dino-towards-a-unified-transformer-based-1","paper_url":"https://arxiv.org/abs/2206.02777v3","paper_title":"Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation","code":"https://github.com/PaddlePaddle/PaddleDetection","n_code_links":10,"official":{"repos":["idea-research/maskdino"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":11,"n_constructed":0,"n_ran_checked":2,"n_instrument":9,"n_unverified":2,"n_samples":13,"n_pointer_only_licence":13,"sample_list":"/paper/mask-dino-towards-a-unified-transformer-based-1#ran","syntology_url":"https://syntology.ai/paper/2206.02777","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.02777"}}}},{"rank_in_archive_order":12,"model":"ViT-Adapter-L (Mask2Former, BEiT pretrain)","metrics":{"Params (M)":"571","Validation mIoU":"60.5"},"uses_additional_data":true,"paper_date":"2022-05-17","paper":"/paper/vision-transformer-adapter-for-dense","paper_url":"https://arxiv.org/abs/2205.08534v4","paper_title":"Vision Transformer Adapter for Dense Predictions","code":"https://github.com/czczup/vit-adapter","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":13,"model":"DINOv2 (ViT-g/14 frozen model, w/ ViT-Adapter + Mask2former)","metrics":{"Params (M)":"1080","Validation mIoU":"60.2"},"uses_additional_data":false,"paper_date":"2023-04-14","paper":"/paper/dinov2-learning-robust-visual-features","paper_url":"https://arxiv.org/abs/2304.07193v2","paper_title":"DINOv2: Learning Robust Visual Features without Supervision","code":"https://github.com/huggingface/transformers","n_code_links":26,"official":{"repos":["facebookresearch/dinov2"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":39,"n_constructed":13,"n_ran_checked":32,"n_instrument":7,"n_unverified":7,"n_samples":46,"n_pointer_only_licence":12,"sample_list":"/paper/dinov2-learning-robust-visual-features#ran","syntology_url":"https://syntology.ai/paper/2304.07193","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.07193"}}}},{"rank_in_archive_order":14,"model":"ViT-P (OneFormer, DiNAT-L)","metrics":{"Params (M)":"309","Validation mIoU":"59.9"},"uses_additional_data":false,"paper_date":"2025-05-26","paper":"/paper/the-missing-point-in-vision-transformers-for","paper_url":"https://arxiv.org/abs/2505.19795v1","paper_title":"The Missing Point in Vision Transformers for Universal Image Segmentation","code":"https://github.com/sajjad-sh33/vit-p","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":15,"model":"SwinV2-G(UperNet)","metrics":{"Validation mIoU":"59.9"},"uses_additional_data":true,"paper_date":"2021-11-18","paper":"/paper/swin-transformer-v2-scaling-up-capacity-and","paper_url":"https://arxiv.org/abs/2111.09883v2","paper_title":"Swin Transformer V2: Scaling Up Capacity and Resolution","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":23,"official":{"repos":["microsoft/Swin-Transformer"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":17,"n_constructed":0,"n_ran_checked":14,"n_instrument":3,"n_unverified":13,"n_samples":30,"n_pointer_only_licence":4,"sample_list":"/paper/swin-transformer-v2-scaling-up-capacity-and#ran","syntology_url":"https://syntology.ai/paper/2111.09883","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.09883"}}}},{"rank_in_archive_order":16,"model":"PIIP-LH6B(UperNet)","metrics":{"Validation mIoU":"59.9"},"uses_additional_data":false,"paper_date":"2024-06-06","paper":"/paper/parameter-inverted-image-pyramid-networks","paper_url":"https://arxiv.org/abs/2406.04330v2","paper_title":"Parameter-Inverted Image Pyramid Networks","code":"https://github.com/opengvlab/piip","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":17,"model":"SERNet-Former","metrics":{"Validation mIoU":"59.35"},"uses_additional_data":false,"paper_date":"2024-01-28","paper":"/paper/sernet-former-semantic-segmentation-by","paper_url":"https://arxiv.org/abs/2401.15741v7","paper_title":"SERNet-Former: Semantic Segmentation by Efficient Residual Network with Attention-Boosting Gates and Attention-Fusion Networks","code":"https://github.com/serdarch/sernet-former","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":18,"model":"FocalNet-L (Mask2Former)","metrics":{"Validation mIoU":"58.5"},"uses_additional_data":true,"paper_date":"2022-03-22","paper":"/paper/focal-modulation-networks","paper_url":"https://arxiv.org/abs/2203.11926v3","paper_title":"Focal Modulation Networks","code":"https://github.com/PaddlePaddle/PaddleDetection","n_code_links":9,"official":{"repos":["microsoft/FocalNet"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0,"sample_list":"/paper/focal-modulation-networks#ran","syntology_url":"https://syntology.ai/paper/2203.11926","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.11926"}}}},{"rank_in_archive_order":19,"model":"ViT-Adapter-L (UperNet, BEiT pretrain)","metrics":{"Params (M)":"451","Validation mIoU":"58.4"},"uses_additional_data":false,"paper_date":"2022-05-17","paper":"/paper/vision-transformer-adapter-for-dense","paper_url":"https://arxiv.org/abs/2205.08534v4","paper_title":"Vision Transformer Adapter for Dense Predictions","code":"https://github.com/czczup/vit-adapter","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":20,"model":"RSSeg-ViT-L (BEiT pretrain)","metrics":{"Params (M)":"330","Validation mIoU":"58.4"},"uses_additional_data":false,"paper_date":"2022-12-28","paper":"/paper/representation-separation-for-semantic","paper_url":"https://arxiv.org/abs/2212.13764v1","paper_title":"Representation Separation for Semantic Segmentation with Vision Transformers","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":21,"model":"EoMT (DINOv2-L, single-scale, 512x512)","metrics":{"GFLOPs":"721","GFLOPs (512 x 512)":"721","Mean IoU (class)":"58.4","Params (M)":"316","Validation mIoU":"58.4"},"uses_additional_data":false,"paper_date":"2025-03-24","paper":"/paper/your-vit-is-secretly-an-image-segmentation-1","paper_url":"https://arxiv.org/abs/2503.19108v1","paper_title":"Your ViT is Secretly an Image Segmentation Model","code":"https://github.com/tue-mps/eomt","n_code_links":1,"official":{"repos":["tue-mps/eomt"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_samples":2,"n_pointer_only_licence":0,"sample_list":"/paper/your-vit-is-secretly-an-image-segmentation-1#ran","syntology_url":"https://syntology.ai/paper/2503.19108","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.19108"}}}},{"rank_in_archive_order":22,"model":"SegViT-v2 (BEiT-v2-Large)","metrics":{"GFLOPs (512 x 512)":"637.9","Validation mIoU":"58.2"},"uses_additional_data":false,"paper_date":"2023-06-09","paper":"/paper/segvitv2-exploring-efficient-and-continual","paper_url":"https://arxiv.org/abs/2306.06289v2","paper_title":"SegViTv2: Exploring Efficient and Continual Semantic Segmentation with Plain Vision Transformers","code":"https://github.com/zbwxp/SegVit","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":23,"model":"SeMask (SeMask Swin-L FaPN-Mask2Former)","metrics":{"Validation mIoU":"58.2"},"uses_additional_data":false,"paper_date":"2021-12-23","paper":"/paper/semask-semantically-masked-transformers-for-1","paper_url":"https://arxiv.org/abs/2112.12782v3","paper_title":"SeMask: Semantically Masked Transformers for Semantic Segmentation","code":"https://github.com/Picsart-AI-Research/SeMask-Segmentation","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":24,"model":"SeMask (SeMask Swin-L MSFaPN-Mask2Former)","metrics":{"Validation mIoU":"58.2"},"uses_additional_data":false,"paper_date":"2021-12-23","paper":"/paper/semask-semantically-masked-transformers-for-1","paper_url":"https://arxiv.org/abs/2112.12782v3","paper_title":"SeMask: Semantically Masked Transformers for Semantic Segmentation","code":"https://github.com/Picsart-AI-Research/SeMask-Segmentation","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":25,"model":"DiNAT-L (Mask2Former)","metrics":{"Validation mIoU":"58.1"},"uses_additional_data":false,"paper_date":"2022-09-29","paper":"/paper/dilated-neighborhood-attention-transformer","paper_url":"https://arxiv.org/abs/2209.15001v3","paper_title":"Dilated Neighborhood Attention Transformer","code":"https://github.com/huggingface/transformers","n_code_links":7,"official":null,"syntology":null},{"rank_in_archive_order":26,"model":"HorNet-L (Mask2Former)","metrics":{"Validation mIoU":"57.9"},"uses_additional_data":false,"paper_date":"2022-07-28","paper":"/paper/hornet-efficient-high-order-spatial","paper_url":"https://arxiv.org/abs/2207.14284v3","paper_title":"HorNet: Efficient High-Order Spatial Interactions with Recursive Gated Convolutions","code":"https://github.com/open-mmlab/mmclassification","n_code_links":8,"official":{"repos":["raoyongming/hornet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0,"sample_list":"/paper/hornet-efficient-high-order-spatial#ran","syntology_url":"https://syntology.ai/paper/2207.14284","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.14284"}}}},{"rank_in_archive_order":27,"model":"Mask2Former (SwinL-FaPN)","metrics":{"Validation mIoU":"57.7"},"uses_additional_data":false,"paper_date":"2021-12-02","paper":"/paper/masked-attention-mask-transformer-for","paper_url":"https://arxiv.org/abs/2112.01527v3","paper_title":"Masked-attention Mask Transformer for Universal Image Segmentation","code":"https://github.com/huggingface/transformers","n_code_links":7,"official":{"repos":["facebookresearch/Mask2Former"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":7,"n_constructed":0,"n_ran_checked":1,"n_instrument":6,"n_unverified":1,"n_samples":8,"n_pointer_only_licence":0,"sample_list":"/paper/masked-attention-mask-transformer-for#ran","syntology_url":"https://syntology.ai/paper/2112.01527","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.01527"}}}},{"rank_in_archive_order":28,"model":"FASeg (SwinL)","metrics":{"Validation mIoU":"57.7"},"uses_additional_data":false,"paper_date":"2022-04-04","paper":"/paper/dynamic-focus-aware-positional-queries-for","paper_url":"https://arxiv.org/abs/2204.01244v3","paper_title":"Dynamic Focus-aware Positional Queries for Semantic Segmentation","code":"https://github.com/ziplab/faseg","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":29,"model":"RR (BEiT-L)","metrics":{"Validation mIoU":"57.7"},"uses_additional_data":false,"paper_date":"2022-04-05","paper":"/paper/region-rebalance-for-long-tailed-semantic","paper_url":"https://arxiv.org/abs/2204.01969v1","paper_title":"Region Rebalance for Long-Tailed Semantic Segmentation","code":"https://github.com/dvlab-research/parametric-contrastive-learning","n_code_links":5,"official":null,"syntology":null},{"rank_in_archive_order":30,"model":"MOAT-4 (IN-22K pretraining, single-scale)","metrics":{"Params (M)":"496","Validation mIoU":"57.6"},"uses_additional_data":false,"paper_date":"2022-10-04","paper":"/paper/moat-alternating-mobile-convolution-and","paper_url":"https://arxiv.org/abs/2210.01820v2","paper_title":"MOAT: Alternating Mobile Convolution and Attention Brings Strong Vision Models","code":"https://github.com/google-research/deeplab2","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":31,"model":"Frozen Backbone, SwinV2-G-ext22K (Mask2Former)","metrics":{"Validation mIoU":"57.6"},"uses_additional_data":false,"paper_date":"2022-11-03","paper":"/paper/could-giant-pretrained-image-models-extract","paper_url":"https://arxiv.org/abs/2211.02043v1","paper_title":"Could Giant Pretrained Image Models Extract Universal Representations?","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":32,"model":"SeMask (SeMask Swin-L Mask2Former)","metrics":{"Validation mIoU":"57.5"},"uses_additional_data":false,"paper_date":"2021-12-23","paper":"/paper/semask-semantically-masked-transformers-for-1","paper_url":"https://arxiv.org/abs/2112.12782v3","paper_title":"SeMask: Semantically Masked Transformers for Semantic Segmentation","code":"https://github.com/Picsart-AI-Research/SeMask-Segmentation","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":33,"model":"Mask2Former (SwinL)","metrics":{"Validation mIoU":"57.3"},"uses_additional_data":false,"paper_date":"2021-12-02","paper":"/paper/masked-attention-mask-transformer-for","paper_url":"https://arxiv.org/abs/2112.01527v3","paper_title":"Masked-attention Mask Transformer for Universal Image Segmentation","code":"https://github.com/huggingface/transformers","n_code_links":7,"official":{"repos":["facebookresearch/Mask2Former"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":7,"n_constructed":0,"n_ran_checked":1,"n_instrument":6,"n_unverified":1,"n_samples":8,"n_pointer_only_licence":0,"sample_list":"/paper/masked-attention-mask-transformer-for#ran","syntology_url":"https://syntology.ai/paper/2112.01527","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.01527"}}}},{"rank_in_archive_order":34,"model":"SenFormer (BEiT-L)","metrics":{"Validation mIoU":"57.1"},"uses_additional_data":true,"paper_date":"2021-11-26","paper":"/paper/efficient-self-ensemble-framework-for-1","paper_url":"https://arxiv.org/abs/2111.13280v2","paper_title":"Efficient Self-Ensemble for Semantic Segmentation","code":"https://github.com/WalBouss/SenFormer","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":35,"model":"BEiT-L (ViT+UperNet)","metrics":{"Validation mIoU":"57.0"},"uses_additional_data":false,"paper_date":"2021-06-15","paper":"/paper/beit-bert-pre-training-of-image-transformers","paper_url":"https://arxiv.org/abs/2106.08254v2","paper_title":"BEiT: BERT Pre-Training of Image Transformers","code":"https://github.com/huggingface/transformers","n_code_links":14,"official":{"repos":["microsoft/unilm"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":6,"n_constructed":2,"n_ran_checked":4,"n_instrument":2,"n_unverified":5,"n_samples":11,"n_pointer_only_licence":0,"sample_list":"/paper/beit-bert-pre-training-of-image-transformers#ran","syntology_url":"https://syntology.ai/paper/2106.08254","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.08254"}}}},{"rank_in_archive_order":36,"model":"SeMask(SeMask Swin-L MSFaPN-Mask2Former, single-scale)","metrics":{"Validation mIoU":"57.0"},"uses_additional_data":false,"paper_date":"2021-12-23","paper":"/paper/semask-semantically-masked-transformers-for-1","paper_url":"https://arxiv.org/abs/2112.12782v3","paper_title":"SeMask: Semantically Masked Transformers for Semantic Segmentation","code":"https://github.com/Picsart-AI-Research/SeMask-Segmentation","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":37,"model":"MetaPrompt-SD","metrics":{"Validation mIoU":"56.8"},"uses_additional_data":false,"paper_date":"2023-12-22","paper":"/paper/harnessing-diffusion-models-for-visual","paper_url":"https://arxiv.org/abs/2312.14733v1","paper_title":"Harnessing Diffusion Models for Visual Perception with Meta Prompts","code":"https://github.com/fudan-zvg/meta-prompts","n_code_links":1,"official":{"repos":["fudan-zvg/meta-prompts"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":0,"n_samples":6,"n_pointer_only_licence":4,"sample_list":"/paper/harnessing-diffusion-models-for-visual#ran","syntology_url":"https://syntology.ai/paper/2312.14733","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.14733"}}}},{"rank_in_archive_order":38,"model":"FaPN (MaskFormer, Swin-L, ImageNet-22k pretrain)","metrics":{"Validation mIoU":"56.7"},"uses_additional_data":false,"paper_date":"2021-08-16","paper":"/paper/fapn-feature-aligned-pyramid-network-for","paper_url":"https://arxiv.org/abs/2108.07058v2","paper_title":"FaPN: Feature-aligned Pyramid Network for Dense Image Prediction","code":"https://github.com/sithu31296/semantic-segmentation","n_code_links":3,"official":{"repos":["EMI-Group/FaPN"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":0,"sample_list":"/paper/fapn-feature-aligned-pyramid-network-for#ran","syntology_url":"https://syntology.ai/paper/2108.07058","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.07058"}}}},{"rank_in_archive_order":39,"model":"MOAT-3 (IN-22K pretraining, single-scale)","metrics":{"Params (M)":"198","Validation mIoU":"56.5"},"uses_additional_data":false,"paper_date":"2022-10-04","paper":"/paper/moat-alternating-mobile-convolution-and","paper_url":"https://arxiv.org/abs/2210.01820v2","paper_title":"MOAT: Alternating Mobile Convolution and Attention Brings Strong Vision Models","code":"https://github.com/google-research/deeplab2","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":40,"model":"Mask2Former (Swin-L-FaPN)","metrics":{"Validation mIoU":"56.4"},"uses_additional_data":false,"paper_date":"2021-12-02","paper":"/paper/masked-attention-mask-transformer-for","paper_url":"https://arxiv.org/abs/2112.01527v3","paper_title":"Masked-attention Mask Transformer for Universal Image Segmentation","code":"https://github.com/huggingface/transformers","n_code_links":7,"official":{"repos":["facebookresearch/Mask2Former"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":7,"n_constructed":0,"n_ran_checked":1,"n_instrument":6,"n_unverified":1,"n_samples":8,"n_pointer_only_licence":0,"sample_list":"/paper/masked-attention-mask-transformer-for#ran","syntology_url":"https://syntology.ai/paper/2112.01527","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.01527"}}}},{"rank_in_archive_order":41,"model":"SeMask (SeMask Swin-L MaskFormer)","metrics":{"Validation mIoU":"56.2"},"uses_additional_data":false,"paper_date":"2021-12-23","paper":"/paper/semask-semantically-masked-transformers-for-1","paper_url":"https://arxiv.org/abs/2112.12782v3","paper_title":"SeMask: Semantically Masked Transformers for Semantic Segmentation","code":"https://github.com/Picsart-AI-Research/SeMask-Segmentation","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":42,"model":"dBOT ViT-L (CLIP)","metrics":{"Validation mIoU":"56.2"},"uses_additional_data":false,"paper_date":"2022-09-08","paper":"/paper/exploring-target-representations-for-masked","paper_url":"https://arxiv.org/abs/2209.03917v3","paper_title":"Exploring Target Representations for Masked Autoencoders","code":"https://github.com/liuxingbin/dbot","n_code_links":1,"official":{"repos":["liuxingbin/dbot"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":2,"n_samples":13,"n_pointer_only_licence":2,"sample_list":"/paper/exploring-target-representations-for-masked#ran","syntology_url":"https://syntology.ai/paper/2209.03917","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.03917"}}}},{"rank_in_archive_order":43,"model":"Mask2Former+CBL(Swin-B)","metrics":{"Validation mIoU":"56.1"},"uses_additional_data":false,"paper_date":"2023-07-05","paper":"/paper/conditional-boundary-loss-for-semantic","paper_url":"https://ieeexplore.ieee.org/document/10173725","paper_title":"Conditional Boundary Loss for Semantic Segmentation","code":"https://github.com/dywu98/CBL-Conditional-Boundary-Loss","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":44,"model":"TADP","metrics":{"Validation mIoU":"55.9"},"uses_additional_data":false,"paper_date":"2023-09-29","paper":"/paper/text-image-alignment-for-diffusion-based","paper_url":"https://arxiv.org/abs/2310.00031v3","paper_title":"Text-image Alignment for Diffusion-based Perception","code":"https://github.com/damaggu/tadp","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":45,"model":"CSWin-L (UperNet, ImageNet-22k pretrain)","metrics":{"Validation mIoU":"55.70"},"uses_additional_data":false,"paper_date":"2021-07-01","paper":"/paper/cswin-transformer-a-general-vision","paper_url":"https://arxiv.org/abs/2107.00652v3","paper_title":"CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows","code":"https://github.com/PaddlePaddle/PaddleClas","n_code_links":7,"official":{"repos":["microsoft/CSWin-Transformer"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":2,"n_samples":6,"n_pointer_only_licence":0,"sample_list":"/paper/cswin-transformer-a-general-vision#ran","syntology_url":"https://syntology.ai/paper/2107.00652","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.00652"}}}},{"rank_in_archive_order":46,"model":"UniRepLKNet-XL","metrics":{"Validation mIoU":"55.6"},"uses_additional_data":false,"paper_date":"2023-11-27","paper":"/paper/unireplknet-a-universal-perception-large","paper_url":"https://arxiv.org/abs/2311.15599v2","paper_title":"UniRepLKNet: A Universal Perception Large-Kernel ConvNet for Audio, Video, Point Cloud, Time-Series and Image Recognition","code":"https://github.com/ailab-cvc/unireplknet","n_code_links":3,"official":{"repos":["ailab-cvc/unireplknet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_samples":2,"n_pointer_only_licence":0,"sample_list":"/paper/unireplknet-a-universal-perception-large#ran","syntology_url":"https://syntology.ai/paper/2311.15599","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.15599"}}}},{"rank_in_archive_order":47,"model":"Focal-L (UperNet, ImageNet-22k pretrain)","metrics":{"Validation mIoU":"55.40"},"uses_additional_data":false,"paper_date":"2021-07-01","paper":"/paper/focal-self-attention-for-local-global","paper_url":"https://arxiv.org/abs/2107.00641v1","paper_title":"Focal Self-attention for Local-Global Interactions in Vision Transformers","code":"https://github.com/BR-IDL/PaddleViT/tree/develop/image_classification/Focal_Transformer","n_code_links":3,"official":{"repos":["microsoft/Focal-Transformer"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":2,"sample_list":"/paper/focal-self-attention-for-local-global#ran","syntology_url":"https://syntology.ai/paper/2107.00641","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.00641"}}}},{"rank_in_archive_order":48,"model":"InternImage-XL","metrics":{"GFLOPs":"3142","Params (M)":"368","Validation mIoU":"55.3"},"uses_additional_data":false,"paper_date":"2022-11-10","paper":"/paper/internimage-exploring-large-scale-vision","paper_url":"https://arxiv.org/abs/2211.05778v4","paper_title":"InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions","code":"https://github.com/opengvlab/internimage","n_code_links":3,"official":{"repos":["opengvlab/internimage"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["listed"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":0,"sample_list":"/paper/internimage-exploring-large-scale-vision#ran","syntology_url":"https://syntology.ai/paper/2211.05778","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.05778"}}}},{"rank_in_archive_order":49,"model":"dBOT ViT-L","metrics":{"Validation mIoU":"55.2"},"uses_additional_data":false,"paper_date":"2022-09-08","paper":"/paper/exploring-target-representations-for-masked","paper_url":"https://arxiv.org/abs/2209.03917v3","paper_title":"Exploring Target Representations for Masked Autoencoders","code":"https://github.com/liuxingbin/dbot","n_code_links":1,"official":{"repos":["liuxingbin/dbot"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":2,"n_samples":13,"n_pointer_only_licence":2,"sample_list":"/paper/exploring-target-representations-for-masked#ran","syntology_url":"https://syntology.ai/paper/2209.03917","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.03917"}}}},{"rank_in_archive_order":50,"model":"Mask2Former(Swin-B)","metrics":{"Validation mIoU":"55.1"},"uses_additional_data":false,"paper_date":"2021-12-02","paper":"/paper/masked-attention-mask-transformer-for","paper_url":"https://arxiv.org/abs/2112.01527v3","paper_title":"Masked-attention Mask Transformer for Universal Image Segmentation","code":"https://github.com/huggingface/transformers","n_code_links":7,"official":{"repos":["facebookresearch/Mask2Former"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":7,"n_constructed":0,"n_ran_checked":1,"n_instrument":6,"n_unverified":1,"n_samples":8,"n_pointer_only_licence":0,"sample_list":"/paper/masked-attention-mask-transformer-for#ran","syntology_url":"https://syntology.ai/paper/2112.01527","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.01527"}}}},{"rank_in_archive_order":51,"model":"ConvNeXt V2-H (FCMAE)","metrics":{"Validation mIoU":"55"},"uses_additional_data":false,"paper_date":"2023-01-02","paper":"/paper/convnext-v2-co-designing-and-scaling-convnets","paper_url":"https://arxiv.org/abs/2301.00808v1","paper_title":"ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":17,"official":{"repos":["facebookresearch/convnext-v2"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":13,"n_constructed":6,"n_ran_checked":10,"n_instrument":3,"n_unverified":1,"n_samples":14,"n_pointer_only_licence":12,"sample_list":"/paper/convnext-v2-co-designing-and-scaling-convnets#ran","syntology_url":"https://syntology.ai/paper/2301.00808","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.00808"}}}},{"rank_in_archive_order":52,"model":"UniRepLKNet-L++","metrics":{"Validation mIoU":"55"},"uses_additional_data":false,"paper_date":"2023-11-27","paper":"/paper/unireplknet-a-universal-perception-large","paper_url":"https://arxiv.org/abs/2311.15599v2","paper_title":"UniRepLKNet: A Universal Perception Large-Kernel ConvNet for Audio, Video, Point Cloud, Time-Series and Image Recognition","code":"https://github.com/ailab-cvc/unireplknet","n_code_links":3,"official":{"repos":["ailab-cvc/unireplknet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_samples":2,"n_pointer_only_licence":0,"sample_list":"/paper/unireplknet-a-universal-perception-large#ran","syntology_url":"https://syntology.ai/paper/2311.15599","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.15599"}}}},{"rank_in_archive_order":53,"model":"DiNAT-Large (UperNet)","metrics":{"Validation mIoU":"54.9"},"uses_additional_data":false,"paper_date":"2022-09-29","paper":"/paper/dilated-neighborhood-attention-transformer","paper_url":"https://arxiv.org/abs/2209.15001v3","paper_title":"Dilated Neighborhood Attention Transformer","code":"https://github.com/huggingface/transformers","n_code_links":7,"official":null,"syntology":null},{"rank_in_archive_order":54,"model":"MaskFormer+CBL(Swin-B)","metrics":{"Validation mIoU":"54.9"},"uses_additional_data":false,"paper_date":"2023-07-05","paper":"/paper/conditional-boundary-loss-for-semantic","paper_url":"https://ieeexplore.ieee.org/document/10173725","paper_title":"Conditional Boundary Loss for Semantic Segmentation","code":"https://github.com/dywu98/CBL-Conditional-Boundary-Loss","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":55,"model":"TransNeXt-Base (IN-1K pretrain, Mask2Former, 512)","metrics":{"Params (M)":"109","Validation mIoU":"54.7"},"uses_additional_data":false,"paper_date":"2023-11-28","paper":"/paper/transnext-robust-foveal-visual-perception-for","paper_url":"https://arxiv.org/abs/2311.17132v3","paper_title":"TransNeXt: Robust Foveal Visual Perception for Vision Transformers","code":"https://github.com/Westlake-AI/openmixup","n_code_links":4,"official":{"repos":["daishiresearch/transnext"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":0,"n_samples":5,"n_pointer_only_licence":0,"sample_list":"/paper/transnext-robust-foveal-visual-perception-for#ran","syntology_url":"https://syntology.ai/paper/2311.17132","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.17132"}}}},{"rank_in_archive_order":56,"model":"MOAT-2 (IN-22K pretraining, single-scale)","metrics":{"Params (M)":"81","Validation mIoU":"54.7"},"uses_additional_data":false,"paper_date":"2022-10-04","paper":"/paper/moat-alternating-mobile-convolution-and","paper_url":"https://arxiv.org/abs/2210.01820v2","paper_title":"MOAT: Alternating Mobile Convolution and Attention Brings Strong Vision Models","code":"https://github.com/google-research/deeplab2","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":57,"model":"CAE (ViT-L, UperNet)","metrics":{"Validation mIoU":"54.7"},"uses_additional_data":false,"paper_date":"2022-02-07","paper":"/paper/context-autoencoder-for-self-supervised","paper_url":"https://arxiv.org/abs/2202.03026v3","paper_title":"Context Autoencoder for Self-Supervised Representation Learning","code":"https://github.com/open-mmlab/mmselfsup","n_code_links":6,"official":null,"syntology":null},{"rank_in_archive_order":58,"model":"VAN-B6","metrics":{"Validation mIoU":"54.7"},"uses_additional_data":false,"paper_date":"2022-02-20","paper":"/paper/visual-attention-network","paper_url":"https://arxiv.org/abs/2202.09741v5","paper_title":"Visual Attention Network","code":"https://github.com/huggingface/transformers","n_code_links":21,"official":{"repos":["Visual-Attention-Network/VAN-Classification"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_samples":6,"n_pointer_only_licence":0,"sample_list":"/paper/visual-attention-network#ran","syntology_url":"https://syntology.ai/paper/2202.09741","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.09741"}}}},{"rank_in_archive_order":59,"model":"DiNAT_s-Large (UperNet)","metrics":{"Validation mIoU":"54.6"},"uses_additional_data":false,"paper_date":"2022-09-29","paper":"/paper/dilated-neighborhood-attention-transformer","paper_url":"https://arxiv.org/abs/2209.15001v3","paper_title":"Dilated Neighborhood Attention Transformer","code":"https://github.com/huggingface/transformers","n_code_links":7,"official":null,"syntology":null},{"rank_in_archive_order":60,"model":"DDP (Swin-L, step-3)","metrics":{"Params (M)":"207","Validation mIoU":"54.4"},"uses_additional_data":false,"paper_date":"2023-03-30","paper":"/paper/ddp-diffusion-model-for-dense-visual","paper_url":"https://arxiv.org/abs/2303.17559v2","paper_title":"DDP: Diffusion Model for Dense Visual Prediction","code":"https://github.com/jiyuanfeng/ddp","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":61,"model":"PatchDiverse + Swin-L (multi-scale test, upernet, ImageNet22k pretrain)","metrics":{"Validation mIoU":"54.4"},"uses_additional_data":false,"paper_date":"2021-04-26","paper":"/paper/improve-vision-transformers-training-by","paper_url":"https://arxiv.org/abs/2104.12753v3","paper_title":"Vision Transformers with Patch Diversification","code":"https://github.com/ChengyueGongR/PatchVisionTransformer","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":62,"model":"VOLO-D5","metrics":{"Validation mIoU":"54.3"},"uses_additional_data":false,"paper_date":"2021-06-24","paper":"/paper/volo-vision-outlooker-for-visual-recognition","paper_url":"https://arxiv.org/abs/2106.13112v2","paper_title":"VOLO: Vision Outlooker for Visual Recognition","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":7,"official":{"repos":["rwightman/pytorch-image-models","sail-sg/volo"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":1,"n_samples":6,"n_pointer_only_licence":0,"sample_list":"/paper/volo-vision-outlooker-for-visual-recognition#ran","syntology_url":"https://syntology.ai/paper/2106.13112","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.13112"}}}},{"rank_in_archive_order":63,"model":"K-Net","metrics":{"Validation mIoU":"54.3"},"uses_additional_data":false,"paper_date":"2021-06-28","paper":"/paper/k-net-towards-unified-image-segmentation","paper_url":"https://arxiv.org/abs/2106.14855v2","paper_title":"K-Net: Towards Unified Image Segmentation","code":"https://github.com/zwwwayne/k-net","n_code_links":1,"official":{"repos":["zwwwayne/k-net"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0,"sample_list":"/paper/k-net-towards-unified-image-segmentation#ran","syntology_url":"https://syntology.ai/paper/2106.14855","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.14855"}}}},{"rank_in_archive_order":64,"model":"GPaCo (Swin-L)","metrics":{"Validation mIoU":"54.3"},"uses_additional_data":false,"paper_date":"2022-09-26","paper":"/paper/generalized-parametric-contrastive-learning","paper_url":"https://arxiv.org/abs/2209.12400v2","paper_title":"Generalized Parametric Contrastive Learning","code":"https://github.com/dvlab-research/parametric-contrastive-learning","n_code_links":4,"official":null,"syntology":null},{"rank_in_archive_order":65,"model":"SenFormer (Swin-L)","metrics":{"Validation mIoU":"54.2"},"uses_additional_data":true,"paper_date":"2021-11-26","paper":"/paper/efficient-self-ensemble-framework-for-1","paper_url":"https://arxiv.org/abs/2111.13280v2","paper_title":"Efficient Self-Ensemble for Semantic Segmentation","code":"https://github.com/WalBouss/SenFormer","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":66,"model":"Swin V2-H","metrics":{"Validation mIoU":"54.2"},"uses_additional_data":false,"paper_date":"2023-01-02","paper":"/paper/convnext-v2-co-designing-and-scaling-convnets","paper_url":"https://arxiv.org/abs/2301.00808v1","paper_title":"ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":17,"official":{"repos":["facebookresearch/convnext-v2"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":13,"n_constructed":6,"n_ran_checked":10,"n_instrument":3,"n_unverified":1,"n_samples":14,"n_pointer_only_licence":12,"sample_list":"/paper/convnext-v2-co-designing-and-scaling-convnets#ran","syntology_url":"https://syntology.ai/paper/2301.00808","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.00808"}}}},{"rank_in_archive_order":67,"model":"InternImage-L","metrics":{"GFLOPs":"2526","Params (M)":"256","Validation mIoU":"54.1"},"uses_additional_data":false,"paper_date":"2022-11-10","paper":"/paper/internimage-exploring-large-scale-vision","paper_url":"https://arxiv.org/abs/2211.05778v4","paper_title":"InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions","code":"https://github.com/opengvlab/internimage","n_code_links":3,"official":{"repos":["opengvlab/internimage"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["listed"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":0,"sample_list":"/paper/internimage-exploring-large-scale-vision#ran","syntology_url":"https://syntology.ai/paper/2211.05778","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.05778"}}}},{"rank_in_archive_order":68,"model":"TransNeXt-Small (IN-1K pretrain, Mask2Former, 512)","metrics":{"Params (M)":"69","Validation mIoU":"54.1"},"uses_additional_data":false,"paper_date":"2023-11-28","paper":"/paper/transnext-robust-foveal-visual-perception-for","paper_url":"https://arxiv.org/abs/2311.17132v3","paper_title":"TransNeXt: Robust Foveal Visual Perception for Vision Transformers","code":"https://github.com/Westlake-AI/openmixup","n_code_links":4,"official":{"repos":["daishiresearch/transnext"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":0,"n_samples":5,"n_pointer_only_licence":0,"sample_list":"/paper/transnext-robust-foveal-visual-perception-for#ran","syntology_url":"https://syntology.ai/paper/2311.17132","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.17132"}}}},{"rank_in_archive_order":69,"model":"ConvNeXt-XL++","metrics":{"GFLOPs (512 x 512)":"3335","Params (M)":"391","Validation mIoU":"54"},"uses_additional_data":false,"paper_date":"2022-01-10","paper":"/paper/a-convnet-for-the-2020s","paper_url":"https://arxiv.org/abs/2201.03545v2","paper_title":"A ConvNet for the 2020s","code":"https://github.com/keras-team/keras/blob/master/keras/applications/convnext.py","n_code_links":54,"official":{"repos":["facebookresearch/ConvNeXt"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":57,"n_constructed":39,"n_ran_checked":49,"n_instrument":8,"n_unverified":23,"n_samples":80,"n_pointer_only_licence":12,"sample_list":"/paper/a-convnet-for-the-2020s#ran","syntology_url":"https://syntology.ai/paper/2201.03545","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.03545"}}}},{"rank_in_archive_order":70,"model":"Sequential Ensemble (SegFormer)","metrics":{"Params (M)":"216.3","Validation mIoU":"54"},"uses_additional_data":false,"paper_date":"2022-10-08","paper":"/paper/sequential-ensembling-for-semantic","paper_url":"https://arxiv.org/abs/2210.05387v1","paper_title":"Sequential Ensembling for Semantic Segmentation","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":71,"model":"MogaNet-XL (UperNet)","metrics":{"Validation mIoU":"54"},"uses_additional_data":false,"paper_date":"2022-11-07","paper":"/paper/efficient-multi-order-gated-aggregation","paper_url":"https://arxiv.org/abs/2211.03295v3","paper_title":"MogaNet: Multi-order Gated Aggregation Network","code":"https://github.com/chengtan9907/OpenSTL","n_code_links":7,"official":{"repos":["Westlake-AI/MogaNet","Westlake-AI/openmixup","chengtan9907/OpenSTL"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":7,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]},"syntology":{"n_ran":12,"n_constructed":7,"n_ran_checked":10,"n_instrument":2,"n_unverified":3,"n_samples":15,"n_pointer_only_licence":0,"sample_list":"/paper/efficient-multi-order-gated-aggregation#ran","syntology_url":"https://syntology.ai/paper/2211.03295","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.03295"}}}},{"rank_in_archive_order":72,"model":"UniRepLKNet-B++","metrics":{"Validation mIoU":"53.9"},"uses_additional_data":false,"paper_date":"2023-11-27","paper":"/paper/unireplknet-a-universal-perception-large","paper_url":"https://arxiv.org/abs/2311.15599v2","paper_title":"UniRepLKNet: A Universal Perception Large-Kernel ConvNet for Audio, Video, Point Cloud, Time-Series and Image Recognition","code":"https://github.com/ailab-cvc/unireplknet","n_code_links":3,"official":{"repos":["ailab-cvc/unireplknet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_samples":2,"n_pointer_only_licence":0,"sample_list":"/paper/unireplknet-a-universal-perception-large#ran","syntology_url":"https://syntology.ai/paper/2311.15599","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.15599"}}}},{"rank_in_archive_order":73,"model":"MaskFormer(Swin-B)","metrics":{"Validation mIoU":"53.8"},"uses_additional_data":false,"paper_date":"2021-07-13","paper":"/paper/per-pixel-classification-is-not-all-you-need","paper_url":"https://arxiv.org/abs/2107.06278v2","paper_title":"Per-Pixel Classification is Not All You Need for Semantic Segmentation","code":"https://github.com/huggingface/transformers","n_code_links":3,"official":null,"syntology":null},{"rank_in_archive_order":74,"model":"ConvNeXt-L++","metrics":{"GFLOPs (512 x 512)":"2458","Params (M)":"235","Validation mIoU":"53.7"},"uses_additional_data":false,"paper_date":"2022-01-10","paper":"/paper/a-convnet-for-the-2020s","paper_url":"https://arxiv.org/abs/2201.03545v2","paper_title":"A ConvNet for the 2020s","code":"https://github.com/keras-team/keras/blob/master/keras/applications/convnext.py","n_code_links":54,"official":{"repos":["facebookresearch/ConvNeXt"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":57,"n_constructed":39,"n_ran_checked":49,"n_instrument":8,"n_unverified":23,"n_samples":80,"n_pointer_only_licence":12,"sample_list":"/paper/a-convnet-for-the-2020s#ran","syntology_url":"https://syntology.ai/paper/2201.03545","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.03545"}}}},{"rank_in_archive_order":75,"model":"SwinV2-G-HTC++ Liu et al. ([2021a])","metrics":{"Validation mIoU":"53.7"},"uses_additional_data":false,"paper_date":"2021-11-18","paper":"/paper/swin-transformer-v2-scaling-up-capacity-and","paper_url":"https://arxiv.org/abs/2111.09883v2","paper_title":"Swin Transformer V2: Scaling Up Capacity and Resolution","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":23,"official":{"repos":["microsoft/Swin-Transformer"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":17,"n_constructed":0,"n_ran_checked":14,"n_instrument":3,"n_unverified":13,"n_samples":30,"n_pointer_only_licence":4,"sample_list":"/paper/swin-transformer-v2-scaling-up-capacity-and#ran","syntology_url":"https://syntology.ai/paper/2111.09883","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.09883"}}}},{"rank_in_archive_order":76,"model":"ConvNeXt V2-L","metrics":{"Validation mIoU":"53.7"},"uses_additional_data":false,"paper_date":"2023-01-02","paper":"/paper/convnext-v2-co-designing-and-scaling-convnets","paper_url":"https://arxiv.org/abs/2301.00808v1","paper_title":"ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":17,"official":{"repos":["facebookresearch/convnext-v2"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":13,"n_constructed":6,"n_ran_checked":10,"n_instrument":3,"n_unverified":1,"n_samples":14,"n_pointer_only_licence":12,"sample_list":"/paper/convnext-v2-co-designing-and-scaling-convnets#ran","syntology_url":"https://syntology.ai/paper/2301.00808","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.00808"}}}},{"rank_in_archive_order":77,"model":"Seg-L-Mask/16 (MS)","metrics":{"Validation mIoU":"53.63"},"uses_additional_data":false,"paper_date":"2021-05-12","paper":"/paper/segmenter-transformer-for-semantic","paper_url":"https://arxiv.org/abs/2105.05633v3","paper_title":"Segmenter: Transformer for Semantic Segmentation","code":"https://github.com/PaddlePaddle/PaddleSeg","n_code_links":8,"official":{"repos":["rstrudel/segmenter"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":3,"n_samples":7,"n_pointer_only_licence":0,"sample_list":"/paper/segmenter-transformer-for-semantic#ran","syntology_url":"https://syntology.ai/paper/2105.05633","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.05633"}}}},{"rank_in_archive_order":78,"model":"MAE (ViT-L, UperNet)","metrics":{"Validation mIoU":"53.6"},"uses_additional_data":false,"paper_date":"2021-11-11","paper":"/paper/masked-autoencoders-are-scalable-vision","paper_url":"https://arxiv.org/abs/2111.06377v2","paper_title":"Masked Autoencoders Are Scalable Vision Learners","code":"https://github.com/facebookresearch/mae","n_code_links":58,"official":{"repos":["facebookresearch/mae"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"syntology":{"n_ran":86,"n_constructed":40,"n_ran_checked":68,"n_instrument":18,"n_unverified":51,"n_samples":137,"n_pointer_only_licence":78,"sample_list":"/paper/masked-autoencoders-are-scalable-vision#ran","syntology_url":"https://syntology.ai/paper/2111.06377","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.06377"}}}},{"rank_in_archive_order":79,"model":"SeMask (SeMask Swin-L FPN)","metrics":{"Validation mIoU":"53.52"},"uses_additional_data":false,"paper_date":"2021-12-23","paper":"/paper/semask-semantically-masked-transformers-for-1","paper_url":"https://arxiv.org/abs/2112.12782v3","paper_title":"SeMask: Semantically Masked Transformers for Semantic Segmentation","code":"https://github.com/Picsart-AI-Research/SeMask-Segmentation","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":80,"model":"Swin-L (UperNet, ImageNet-22k pretrain)","metrics":{"Test Score":"62.8","Validation mIoU":"53.50"},"uses_additional_data":false,"paper_date":"2021-03-25","paper":"/paper/swin-transformer-hierarchical-vision","paper_url":"https://arxiv.org/abs/2103.14030v2","paper_title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","code":"https://github.com/huggingface/transformers","n_code_links":80,"official":{"repos":["microsoft/Swin-Transformer"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["listed"]},"syntology":{"n_ran":123,"n_constructed":45,"n_ran_checked":79,"n_instrument":44,"n_unverified":84,"n_samples":207,"n_pointer_only_licence":45,"sample_list":"/paper/swin-transformer-hierarchical-vision#ran","syntology_url":"https://syntology.ai/paper/2103.14030","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.14030"}}}},{"rank_in_archive_order":81,"model":"Swin-L","metrics":{"Validation mIoU":"53.5"},"uses_additional_data":false,"paper_date":"2023-01-02","paper":"/paper/convnext-v2-co-designing-and-scaling-convnets","paper_url":"https://arxiv.org/abs/2301.00808v1","paper_title":"ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":17,"official":{"repos":["facebookresearch/convnext-v2"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":13,"n_constructed":6,"n_ran_checked":10,"n_instrument":3,"n_unverified":1,"n_samples":14,"n_pointer_only_licence":12,"sample_list":"/paper/convnext-v2-co-designing-and-scaling-convnets#ran","syntology_url":"https://syntology.ai/paper/2301.00808","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.00808"}}}},{"rank_in_archive_order":82,"model":"TransNeXt-Tiny (IN-1K pretrain, Mask2Former, 512)","metrics":{"Params (M)":"47.5","Validation mIoU":"53.4"},"uses_additional_data":false,"paper_date":"2023-11-28","paper":"/paper/transnext-robust-foveal-visual-perception-for","paper_url":"https://arxiv.org/abs/2311.17132v3","paper_title":"TransNeXt: Robust Foveal Visual Perception for Vision Transformers","code":"https://github.com/Westlake-AI/openmixup","n_code_links":4,"official":{"repos":["daishiresearch/transnext"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":0,"n_samples":5,"n_pointer_only_licence":0,"sample_list":"/paper/transnext-robust-foveal-visual-perception-for#ran","syntology_url":"https://syntology.ai/paper/2311.17132","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.17132"}}}},{"rank_in_archive_order":83,"model":"ConvNeXt-B++","metrics":{"GFLOPs (512 x 512)":"1828","Params (M)":"122","Validation mIoU":"53.1"},"uses_additional_data":false,"paper_date":"2022-01-10","paper":"/paper/a-convnet-for-the-2020s","paper_url":"https://arxiv.org/abs/2201.03545v2","paper_title":"A ConvNet for the 2020s","code":"https://github.com/keras-team/keras/blob/master/keras/applications/convnext.py","n_code_links":54,"official":{"repos":["facebookresearch/ConvNeXt"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":57,"n_constructed":39,"n_ran_checked":49,"n_instrument":8,"n_unverified":23,"n_samples":80,"n_pointer_only_licence":12,"sample_list":"/paper/a-convnet-for-the-2020s#ran","syntology_url":"https://syntology.ai/paper/2201.03545","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.03545"}}}},{"rank_in_archive_order":84,"model":"PatchConvNet-L120 (UperNet)","metrics":{"Validation mIoU":"52.9"},"uses_additional_data":false,"paper_date":"2021-12-27","paper":"/paper/augmenting-convolutional-networks-with","paper_url":"https://arxiv.org/abs/2112.13692v1","paper_title":"Augmenting Convolutional networks with attention-based aggregation","code":"https://github.com/facebookresearch/deit","n_code_links":5,"official":{"repos":["facebookresearch/deit"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0,"sample_list":"/paper/augmenting-convolutional-networks-with#ran","syntology_url":"https://syntology.ai/paper/2112.13692","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.13692"}}}},{"rank_in_archive_order":85,"model":"dBOT ViT-B (CLIP)","metrics":{"Validation mIoU":"52.9"},"uses_additional_data":false,"paper_date":"2022-09-08","paper":"/paper/exploring-target-representations-for-masked","paper_url":"https://arxiv.org/abs/2209.03917v3","paper_title":"Exploring Target Representations for Masked Autoencoders","code":"https://github.com/liuxingbin/dbot","n_code_links":1,"official":{"repos":["liuxingbin/dbot"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":2,"n_samples":13,"n_pointer_only_licence":2,"sample_list":"/paper/exploring-target-representations-for-masked#ran","syntology_url":"https://syntology.ai/paper/2209.03917","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.03917"}}}},{"rank_in_archive_order":86,"model":"PatchConvNet-B120\n(UperNet)","metrics":{"Validation mIoU":"52.8"},"uses_additional_data":false,"paper_date":"2021-12-27","paper":"/paper/augmenting-convolutional-networks-with","paper_url":"https://arxiv.org/abs/2112.13692v1","paper_title":"Augmenting Convolutional networks with attention-based aggregation","code":"https://github.com/facebookresearch/deit","n_code_links":5,"official":{"repos":["facebookresearch/deit"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0,"sample_list":"/paper/augmenting-convolutional-networks-with#ran","syntology_url":"https://syntology.ai/paper/2112.13692","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.13692"}}}},{"rank_in_archive_order":87,"model":"Swin-B","metrics":{"Validation mIoU":"52.8"},"uses_additional_data":false,"paper_date":"2023-01-02","paper":"/paper/convnext-v2-co-designing-and-scaling-convnets","paper_url":"https://arxiv.org/abs/2301.00808v1","paper_title":"ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":17,"official":{"repos":["facebookresearch/convnext-v2"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":13,"n_constructed":6,"n_ran_checked":10,"n_instrument":3,"n_unverified":1,"n_samples":14,"n_pointer_only_licence":12,"sample_list":"/paper/convnext-v2-co-designing-and-scaling-convnets#ran","syntology_url":"https://syntology.ai/paper/2301.00808","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.00808"}}}},{"rank_in_archive_order":88,"model":"UniRepLKNet-S++","metrics":{"Validation mIoU":"52.7"},"uses_additional_data":false,"paper_date":"2023-11-27","paper":"/paper/unireplknet-a-universal-perception-large","paper_url":"https://arxiv.org/abs/2311.15599v2","paper_title":"UniRepLKNet: A Universal Perception Large-Kernel ConvNet for Audio, Video, Point Cloud, Time-Series and Image Recognition","code":"https://github.com/ailab-cvc/unireplknet","n_code_links":3,"official":{"repos":["ailab-cvc/unireplknet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_samples":2,"n_pointer_only_licence":0,"sample_list":"/paper/unireplknet-a-universal-perception-large#ran","syntology_url":"https://syntology.ai/paper/2311.15599","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.15599"}}}},{"rank_in_archive_order":89,"model":"ConvNeXt V2-B","metrics":{"Validation mIoU":"52.1"},"uses_additional_data":false,"paper_date":"2023-01-02","paper":"/paper/convnext-v2-co-designing-and-scaling-convnets","paper_url":"https://arxiv.org/abs/2301.00808v1","paper_title":"ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":17,"official":{"repos":["facebookresearch/convnext-v2"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":13,"n_constructed":6,"n_ran_checked":10,"n_instrument":3,"n_unverified":1,"n_samples":14,"n_pointer_only_licence":12,"sample_list":"/paper/convnext-v2-co-designing-and-scaling-convnets#ran","syntology_url":"https://syntology.ai/paper/2301.00808","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.00808"}}}},{"rank_in_archive_order":90,"model":"DeBiFormer-B (IN1k pretrain, Upernet 160k)","metrics":{"Validation mIoU":"52.0"},"uses_additional_data":false,"paper_date":"2024-10-11","paper":"/paper/debiformer-vision-transformer-with-deformable","paper_url":"https://arxiv.org/abs/2410.08582v1","paper_title":"DeBiFormer: Vision Transformer with Deformable Agent Bi-level Routing Attention","code":"https://github.com/maclong01/DeBiFormer","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":91,"model":"LV-ViT-L (UperNet, MS)","metrics":{"Params (M)":"209","Validation mIoU":"51.8"},"uses_additional_data":false,"paper_date":"2021-04-22","paper":"/paper/token-labeling-training-a-85-5-top-1-accuracy","paper_url":"https://arxiv.org/abs/2104.10858v3","paper_title":"All Tokens Matter: Token Labeling for Training Better Vision Transformers","code":"https://github.com/zihangJiang/TokenLabeling","n_code_links":7,"official":{"repos":["zihangJiang/TokenLabeling"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":2,"n_samples":5,"n_pointer_only_licence":3,"sample_list":"/paper/token-labeling-training-a-85-5-top-1-accuracy#ran","syntology_url":"https://syntology.ai/paper/2104.10858","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.10858"}}}},{"rank_in_archive_order":92,"model":"SegFormer-B5","metrics":{"Params (M)":"84.7","Validation mIoU":"51.8"},"uses_additional_data":true,"paper_date":"2021-05-31","paper":"/paper/segformer-simple-and-efficient-design-for","paper_url":"https://arxiv.org/abs/2105.15203v3","paper_title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","code":"https://github.com/huggingface/transformers","n_code_links":28,"official":{"repos":["NVlabs/SegFormer"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["community","listed","unlocated"]},"syntology":{"n_ran":66,"n_constructed":22,"n_ran_checked":52,"n_instrument":14,"n_unverified":20,"n_samples":86,"n_pointer_only_licence":20,"sample_list":"/paper/segformer-simple-and-efficient-design-for#ran","syntology_url":"https://syntology.ai/paper/2105.15203","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.15203"}}}},{"rank_in_archive_order":93,"model":"BiFormer-B (IN1k pretrain, Upernet 160k)","metrics":{"Validation mIoU":"51.7"},"uses_additional_data":false,"paper_date":"2023-03-15","paper":"/paper/biformer-vision-transformer-with-bi-level","paper_url":"https://arxiv.org/abs/2303.08810v1","paper_title":"BiFormer: Vision Transformer with Bi-Level Routing Attention","code":"https://github.com/rayleizhu/biformer","n_code_links":3,"official":{"repos":["rayleizhu/biformer"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":3,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":6,"n_constructed":5,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_samples":6,"n_pointer_only_licence":0,"sample_list":"/paper/biformer-vision-transformer-with-bi-level#ran","syntology_url":"https://syntology.ai/paper/2303.08810","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.08810"}}}},{"rank_in_archive_order":94,"model":"ConvNeXt V2-L (Supervised)","metrics":{"Validation mIoU":"51.6"},"uses_additional_data":false,"paper_date":"2023-01-02","paper":"/paper/convnext-v2-co-designing-and-scaling-convnets","paper_url":"https://arxiv.org/abs/2301.00808v1","paper_title":"ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":17,"official":{"repos":["facebookresearch/convnext-v2"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":13,"n_constructed":6,"n_ran_checked":10,"n_instrument":3,"n_unverified":1,"n_samples":14,"n_pointer_only_licence":12,"sample_list":"/paper/convnext-v2-co-designing-and-scaling-convnets#ran","syntology_url":"https://syntology.ai/paper/2301.00808","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.00808"}}}},{"rank_in_archive_order":95,"model":"Light-Ham (VAN-Huge)","metrics":{"GFLOPs (512 x 512)":"71.8","Params (M)":"61.1","Validation mIoU":"51.5"},"uses_additional_data":false,"paper_date":"2021-09-09","paper":"/paper/is-attention-better-than-matrix-decomposition-1","paper_url":"https://arxiv.org/abs/2109.04553v2","paper_title":"Is Attention Better Than Matrix Decomposition?","code":"https://github.com/Gsunshine/Enjoy-Hamburger","n_code_links":3,"official":{"repos":["Gsunshine/Enjoy-Hamburger"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3,"sample_list":"/paper/is-attention-better-than-matrix-decomposition-1#ran","syntology_url":"https://syntology.ai/paper/2109.04553","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.04553"}}}},{"rank_in_archive_order":96,"model":"DAT-B++","metrics":{"Validation mIoU":"51.5"},"uses_additional_data":false,"paper_date":"2023-09-04","paper":"/paper/dat-spatially-dynamic-vision-transformer-with","paper_url":"https://arxiv.org/abs/2309.01430v1","paper_title":"DAT++: Spatially Dynamic Vision Transformer with Deformable Attention","code":"https://github.com/leaplabthu/dat","n_code_links":1,"official":{"repos":["leaplabthu/dat"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":2,"n_samples":10,"n_pointer_only_licence":6,"sample_list":"/paper/dat-spatially-dynamic-vision-transformer-with#ran","syntology_url":"https://syntology.ai/paper/2309.01430","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.01430"}}}},{"rank_in_archive_order":97,"model":"CrossFormer (ImageNet1k-pretrain, UPerNet, multi-scale test)","metrics":{"Validation mIoU":"51.4"},"uses_additional_data":false,"paper_date":"2021-07-31","paper":"/paper/crossformer-a-versatile-vision-transformer","paper_url":"https://arxiv.org/abs/2108.00154v2","paper_title":"CrossFormer: A Versatile Vision Transformer Hinging on Cross-scale Attention","code":"https://github.com/cheerss/CrossFormer","n_code_links":4,"official":{"repos":["cheerss/CrossFormer"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0,"sample_list":"/paper/crossformer-a-versatile-vision-transformer#ran","syntology_url":"https://syntology.ai/paper/2108.00154","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.00154"}}}},{"rank_in_archive_order":98,"model":"InternImage-B","metrics":{"GFLOPs":"1185","Params (M)":"128","Validation mIoU":"51.3"},"uses_additional_data":false,"paper_date":"2022-11-10","paper":"/paper/internimage-exploring-large-scale-vision","paper_url":"https://arxiv.org/abs/2211.05778v4","paper_title":"InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions","code":"https://github.com/opengvlab/internimage","n_code_links":3,"official":{"repos":["opengvlab/internimage"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["listed"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":0,"sample_list":"/paper/internimage-exploring-large-scale-vision#ran","syntology_url":"https://syntology.ai/paper/2211.05778","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.05778"}}}},{"rank_in_archive_order":99,"model":"DAT-S++","metrics":{"Validation mIoU":"51.2"},"uses_additional_data":false,"paper_date":"2023-09-04","paper":"/paper/dat-spatially-dynamic-vision-transformer-with","paper_url":"https://arxiv.org/abs/2309.01430v1","paper_title":"DAT++: Spatially Dynamic Vision Transformer with Deformable Attention","code":"https://github.com/leaplabthu/dat","n_code_links":1,"official":{"repos":["leaplabthu/dat"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":2,"n_samples":10,"n_pointer_only_licence":6,"sample_list":"/paper/dat-spatially-dynamic-vision-transformer-with#ran","syntology_url":"https://syntology.ai/paper/2309.01430","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.01430"}}}},{"rank_in_archive_order":100,"model":"ActiveMLP-L(UperNet)","metrics":{"Params (M)":"108","Validation mIoU":"51.1"},"uses_additional_data":false,"paper_date":"2022-03-11","paper":"/paper/activemlp-an-mlp-like-architecture-with","paper_url":"https://arxiv.org/abs/2203.06108v2","paper_title":"Active Token Mixer","code":"https://github.com/microsoft/TokenMixers","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":101,"model":"SegFormer-B4","metrics":{"Params (M)":"64.1","Validation mIoU":"51.1"},"uses_additional_data":true,"paper_date":"2021-05-31","paper":"/paper/segformer-simple-and-efficient-design-for","paper_url":"https://arxiv.org/abs/2105.15203v3","paper_title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","code":"https://github.com/huggingface/transformers","n_code_links":28,"official":{"repos":["NVlabs/SegFormer"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["community","listed","unlocated"]},"syntology":{"n_ran":66,"n_constructed":22,"n_ran_checked":52,"n_instrument":14,"n_unverified":20,"n_samples":86,"n_pointer_only_licence":20,"sample_list":"/paper/segformer-simple-and-efficient-design-for#ran","syntology_url":"https://syntology.ai/paper/2105.15203","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.15203"}}}},{"rank_in_archive_order":102,"model":"PatchConvNet-B60 (UperNet)","metrics":{"Validation mIoU":"51.1"},"uses_additional_data":false,"paper_date":"2021-12-27","paper":"/paper/augmenting-convolutional-networks-with","paper_url":"https://arxiv.org/abs/2112.13692v1","paper_title":"Augmenting Convolutional networks with attention-based aggregation","code":"https://github.com/facebookresearch/deit","n_code_links":5,"official":{"repos":["facebookresearch/deit"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0,"sample_list":"/paper/augmenting-convolutional-networks-with#ran","syntology_url":"https://syntology.ai/paper/2112.13692","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.13692"}}}},{"rank_in_archive_order":103,"model":"Light-Ham (VAN-Large)","metrics":{"GFLOPs (512 x 512)":"55.0","Params (M)":"45.6","Validation mIoU":"51.0"},"uses_additional_data":false,"paper_date":"2021-09-09","paper":"/paper/is-attention-better-than-matrix-decomposition-1","paper_url":"https://arxiv.org/abs/2109.04553v2","paper_title":"Is Attention Better Than Matrix Decomposition?","code":"https://github.com/Gsunshine/Enjoy-Hamburger","n_code_links":3,"official":{"repos":["Gsunshine/Enjoy-Hamburger"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3,"sample_list":"/paper/is-attention-better-than-matrix-decomposition-1#ran","syntology_url":"https://syntology.ai/paper/2109.04553","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.04553"}}}},{"rank_in_archive_order":104,"model":"TEC (Vit-B, Upernet)","metrics":{"Validation mIoU":"51.0"},"uses_additional_data":false,"paper_date":"2022-10-20","paper":"/paper/towards-sustainable-self-supervised-learning","paper_url":"https://arxiv.org/abs/2210.11016v1","paper_title":"Towards Sustainable Self-supervised Learning","code":"https://github.com/sail-sg/tec","n_code_links":1,"official":{"repos":["sail-sg/tec"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":6,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":6,"n_constructed":6,"n_ran_checked":6,"n_instrument":0,"n_unverified":2,"n_samples":8,"n_pointer_only_licence":8,"sample_list":"/paper/towards-sustainable-self-supervised-learning#ran","syntology_url":"https://syntology.ai/paper/2210.11016","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.11016"}}}},{"rank_in_archive_order":105,"model":"UniRepLKNet-S","metrics":{"Validation mIoU":"51"},"uses_additional_data":false,"paper_date":"2023-11-27","paper":"/paper/unireplknet-a-universal-perception-large","paper_url":"https://arxiv.org/abs/2311.15599v2","paper_title":"UniRepLKNet: A Universal Perception Large-Kernel ConvNet for Audio, Video, Point Cloud, Time-Series and Image Recognition","code":"https://github.com/ailab-cvc/unireplknet","n_code_links":3,"official":{"repos":["ailab-cvc/unireplknet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_samples":2,"n_pointer_only_licence":0,"sample_list":"/paper/unireplknet-a-universal-perception-large#ran","syntology_url":"https://syntology.ai/paper/2311.15599","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.15599"}}}},{"rank_in_archive_order":106,"model":"SeMask (SeMask Swin-B FPN)","metrics":{"Params (M)":"96","Validation mIoU":"50.98"},"uses_additional_data":false,"paper_date":"2021-12-23","paper":"/paper/semask-semantically-masked-transformers-for-1","paper_url":"https://arxiv.org/abs/2112.12782v3","paper_title":"SeMask: Semantically Masked Transformers for Semantic Segmentation","code":"https://github.com/Picsart-AI-Research/SeMask-Segmentation","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":107,"model":"InternImage-S","metrics":{"GFLOPs":"1017","Params (M)":"80","Validation mIoU":"50.9"},"uses_additional_data":false,"paper_date":"2022-11-10","paper":"/paper/internimage-exploring-large-scale-vision","paper_url":"https://arxiv.org/abs/2211.05778v4","paper_title":"InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions","code":"https://github.com/opengvlab/internimage","n_code_links":3,"official":{"repos":["opengvlab/internimage"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["listed"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":0,"sample_list":"/paper/internimage-exploring-large-scale-vision#ran","syntology_url":"https://syntology.ai/paper/2211.05778","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.05778"}}}},{"rank_in_archive_order":108,"model":"MogaNet-L (UperNet)","metrics":{"GFLOPs (512 x 512)":"1176","Validation mIoU":"50.9"},"uses_additional_data":false,"paper_date":"2022-11-07","paper":"/paper/efficient-multi-order-gated-aggregation","paper_url":"https://arxiv.org/abs/2211.03295v3","paper_title":"MogaNet: Multi-order Gated Aggregation Network","code":"https://github.com/chengtan9907/OpenSTL","n_code_links":7,"official":{"repos":["Westlake-AI/MogaNet","Westlake-AI/openmixup","chengtan9907/OpenSTL"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":7,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]},"syntology":{"n_ran":12,"n_constructed":7,"n_ran_checked":10,"n_instrument":2,"n_unverified":3,"n_samples":15,"n_pointer_only_licence":0,"sample_list":"/paper/efficient-multi-order-gated-aggregation#ran","syntology_url":"https://syntology.ai/paper/2211.03295","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.03295"}}}},{"rank_in_archive_order":109,"model":"dBOT ViT-B","metrics":{"Validation mIoU":"50.8"},"uses_additional_data":false,"paper_date":"2022-09-08","paper":"/paper/exploring-target-representations-for-masked","paper_url":"https://arxiv.org/abs/2209.03917v3","paper_title":"Exploring Target Representations for Masked Autoencoders","code":"https://github.com/liuxingbin/dbot","n_code_links":1,"official":{"repos":["liuxingbin/dbot"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":2,"n_samples":13,"n_pointer_only_licence":2,"sample_list":"/paper/exploring-target-representations-for-masked#ran","syntology_url":"https://syntology.ai/paper/2209.03917","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.03917"}}}},{"rank_in_archive_order":110,"model":"Upernet-BiFormer-S (IN1k pretrain, Upernet 160k)","metrics":{"Validation mIoU":"50.8"},"uses_additional_data":false,"paper_date":"2023-03-15","paper":"/paper/biformer-vision-transformer-with-bi-level","paper_url":"https://arxiv.org/abs/2303.08810v1","paper_title":"BiFormer: Vision Transformer with Bi-Level Routing Attention","code":"https://github.com/rayleizhu/biformer","n_code_links":3,"official":{"repos":["rayleizhu/biformer"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":3,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":6,"n_constructed":5,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_samples":6,"n_pointer_only_licence":0,"sample_list":"/paper/biformer-vision-transformer-with-bi-level#ran","syntology_url":"https://syntology.ai/paper/2303.08810","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.08810"}}}},{"rank_in_archive_order":111,"model":"UperNet Shuffle-B","metrics":{"Validation mIoU":"50.5"},"uses_additional_data":false,"paper_date":"2021-06-07","paper":"/paper/shuffle-transformer-rethinking-spatial","paper_url":"https://arxiv.org/abs/2106.03650v1","paper_title":"Shuffle Transformer: Rethinking Spatial Shuffle for Vision Transformer","code":"https://github.com/alibaba/EasyCV","n_code_links":4,"official":null,"syntology":{"n_ran":10,"n_constructed":0,"n_ran_checked":6,"n_instrument":4,"n_unverified":2,"n_samples":12,"n_pointer_only_licence":6,"sample_list":"/paper/shuffle-transformer-rethinking-spatial#ran","syntology_url":"https://syntology.ai/paper/2106.03650","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.03650"}}}},{"rank_in_archive_order":112,"model":"ConvNeXt V1-L","metrics":{"Validation mIoU":"50.5"},"uses_additional_data":false,"paper_date":"2023-01-02","paper":"/paper/convnext-v2-co-designing-and-scaling-convnets","paper_url":"https://arxiv.org/abs/2301.00808v1","paper_title":"ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":17,"official":{"repos":["facebookresearch/convnext-v2"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":13,"n_constructed":6,"n_ran_checked":10,"n_instrument":3,"n_unverified":1,"n_samples":14,"n_pointer_only_licence":12,"sample_list":"/paper/convnext-v2-co-designing-and-scaling-convnets#ran","syntology_url":"https://syntology.ai/paper/2301.00808","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.00808"}}}},{"rank_in_archive_order":113,"model":"DiNAT-Base (UperNet)","metrics":{"Validation mIoU":"50.4"},"uses_additional_data":false,"paper_date":"2022-09-29","paper":"/paper/dilated-neighborhood-attention-transformer","paper_url":"https://arxiv.org/abs/2209.15001v3","paper_title":"Dilated Neighborhood Attention Transformer","code":"https://github.com/huggingface/transformers","n_code_links":7,"official":null,"syntology":null},{"rank_in_archive_order":114,"model":"ELSA-Swin-S","metrics":{"Validation mIoU":"50.3"},"uses_additional_data":false,"paper_date":"2021-12-23","paper":"/paper/elsa-enhanced-local-self-attention-for-vision","paper_url":"https://arxiv.org/abs/2112.12786v1","paper_title":"ELSA: Enhanced Local Self-Attention for Vision Transformer","code":"https://github.com/damo-cv/elsa","n_code_links":1,"official":{"repos":["damo-cv/elsa"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0,"sample_list":"/paper/elsa-enhanced-local-self-attention-for-vision#ran","syntology_url":"https://syntology.ai/paper/2112.12786","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.12786"}}}},{"rank_in_archive_order":115,"model":"DAT-T++","metrics":{"Validation mIoU":"50.3"},"uses_additional_data":false,"paper_date":"2023-09-04","paper":"/paper/dat-spatially-dynamic-vision-transformer-with","paper_url":"https://arxiv.org/abs/2309.01430v1","paper_title":"DAT++: Spatially Dynamic Vision Transformer with Deformable Attention","code":"https://github.com/leaplabthu/dat","n_code_links":1,"official":{"repos":["leaplabthu/dat"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":2,"n_samples":10,"n_pointer_only_licence":6,"sample_list":"/paper/dat-spatially-dynamic-vision-transformer-with#ran","syntology_url":"https://syntology.ai/paper/2309.01430","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.01430"}}}},{"rank_in_archive_order":116,"model":"SETR-MLA (160k, MS)","metrics":{"Validation mIoU":"50.28"},"uses_additional_data":false,"paper_date":"2020-12-31","paper":"/paper/rethinking-semantic-segmentation-from-a","paper_url":"https://arxiv.org/abs/2012.15840v3","paper_title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers","code":"https://github.com/PaddlePaddle/PaddleSeg","n_code_links":5,"official":null,"syntology":null},{"rank_in_archive_order":117,"model":"VAN-Large (HamNet)","metrics":{"Params (M)":"55","Validation mIoU":"50.2"},"uses_additional_data":false,"paper_date":"2022-02-20","paper":"/paper/visual-attention-network","paper_url":"https://arxiv.org/abs/2202.09741v5","paper_title":"Visual Attention Network","code":"https://github.com/huggingface/transformers","n_code_links":21,"official":{"repos":["Visual-Attention-Network/VAN-Classification"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_samples":6,"n_pointer_only_licence":0,"sample_list":"/paper/visual-attention-network#ran","syntology_url":"https://syntology.ai/paper/2202.09741","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.09741"}}}},{"rank_in_archive_order":118,"model":"HRViT-b3 (SegFormer, SS)","metrics":{"GFLOPs (512 x 512)":"67.9","Params (M)":"28.7","Validation mIoU":"50.2"},"uses_additional_data":false,"paper_date":"2021-11-01","paper":"/paper/hrvit-multi-scale-high-resolution-vision","paper_url":"https://arxiv.org/abs/2111.01236v2","paper_title":"Multi-Scale High-Resolution Vision Transformer for Semantic Segmentation","code":"https://github.com/facebookresearch/HRViT","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":119,"model":"Twins-SVT-L (UperNet, ImageNet-1k pretrain)","metrics":{"Validation mIoU":"50.2"},"uses_additional_data":false,"paper_date":"2021-04-28","paper":"/paper/twins-revisiting-spatial-attention-design-in","paper_url":"https://arxiv.org/abs/2104.13840v4","paper_title":"Twins: Revisiting the Design of Spatial Attention in Vision Transformers","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":9,"official":{"repos":["Meituan-AutoML/Twins"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2,"sample_list":"/paper/twins-revisiting-spatial-attention-design-in#ran","syntology_url":"https://syntology.ai/paper/2104.13840","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.13840"}}}},{"rank_in_archive_order":120,"model":"MogaNet-B (UperNet)","metrics":{"GFLOPs (512 x 512)":"1050","Validation mIoU":"50.1"},"uses_additional_data":false,"paper_date":"2022-11-07","paper":"/paper/efficient-multi-order-gated-aggregation","paper_url":"https://arxiv.org/abs/2211.03295v3","paper_title":"MogaNet: Multi-order Gated Aggregation Network","code":"https://github.com/chengtan9907/OpenSTL","n_code_links":7,"official":{"repos":["Westlake-AI/MogaNet","Westlake-AI/openmixup","chengtan9907/OpenSTL"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":7,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]},"syntology":{"n_ran":12,"n_constructed":7,"n_ran_checked":10,"n_instrument":2,"n_unverified":3,"n_samples":15,"n_pointer_only_licence":0,"sample_list":"/paper/efficient-multi-order-gated-aggregation#ran","syntology_url":"https://syntology.ai/paper/2211.03295","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.03295"}}}},{"rank_in_archive_order":121,"model":"Seg-B-Mask/16(MS, ViT-B)","metrics":{"Validation mIoU":"50.0"},"uses_additional_data":false,"paper_date":"2021-05-12","paper":"/paper/segmenter-transformer-for-semantic","paper_url":"https://arxiv.org/abs/2105.05633v3","paper_title":"Segmenter: Transformer for Semantic Segmentation","code":"https://github.com/PaddlePaddle/PaddleSeg","n_code_links":8,"official":{"repos":["rstrudel/segmenter"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":3,"n_samples":7,"n_pointer_only_licence":0,"sample_list":"/paper/segmenter-transformer-for-semantic#ran","syntology_url":"https://syntology.ai/paper/2105.05633","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.05633"}}}},{"rank_in_archive_order":122,"model":"iBOT (ViT-B/16)","metrics":{"Validation mIoU":"50.0"},"uses_additional_data":false,"paper_date":"2021-11-15","paper":"/paper/ibot-image-bert-pre-training-with-online","paper_url":"https://arxiv.org/abs/2111.07832v3","paper_title":"iBOT: Image BERT Pre-Training with Online Tokenizer","code":"https://github.com/bytedance/ibot","n_code_links":2,"official":{"repos":["bytedance/ibot"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]},"syntology":{"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0,"sample_list":"/paper/ibot-image-bert-pre-training-with-online#ran","syntology_url":"https://syntology.ai/paper/2111.07832","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.07832"}}}},{"rank_in_archive_order":123,"model":"ConvNeXt-B","metrics":{"GFLOPs (512 x 512)":"1170","Params (M)":"122","Validation mIoU":"49.9"},"uses_additional_data":false,"paper_date":"2022-01-10","paper":"/paper/a-convnet-for-the-2020s","paper_url":"https://arxiv.org/abs/2201.03545v2","paper_title":"A ConvNet for the 2020s","code":"https://github.com/keras-team/keras/blob/master/keras/applications/convnext.py","n_code_links":54,"official":{"repos":["facebookresearch/ConvNeXt"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":57,"n_constructed":39,"n_ran_checked":49,"n_instrument":8,"n_unverified":23,"n_samples":80,"n_pointer_only_licence":12,"sample_list":"/paper/a-convnet-for-the-2020s#ran","syntology_url":"https://syntology.ai/paper/2201.03545","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.03545"}}}},{"rank_in_archive_order":124,"model":"DiNAT-Small (UperNet)","metrics":{"Validation mIoU":"49.9"},"uses_additional_data":false,"paper_date":"2022-09-29","paper":"/paper/dilated-neighborhood-attention-transformer","paper_url":"https://arxiv.org/abs/2209.15001v3","paper_title":"Dilated Neighborhood Attention Transformer","code":"https://github.com/huggingface/transformers","n_code_links":7,"official":null,"syntology":null},{"rank_in_archive_order":125,"model":"ConvNeXt V1-B","metrics":{"Validation mIoU":"49.9"},"uses_additional_data":false,"paper_date":"2023-01-02","paper":"/paper/convnext-v2-co-designing-and-scaling-convnets","paper_url":"https://arxiv.org/abs/2301.00808v1","paper_title":"ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":17,"official":{"repos":["facebookresearch/convnext-v2"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":13,"n_constructed":6,"n_ran_checked":10,"n_instrument":3,"n_unverified":1,"n_samples":14,"n_pointer_only_licence":12,"sample_list":"/paper/convnext-v2-co-designing-and-scaling-convnets#ran","syntology_url":"https://syntology.ai/paper/2301.00808","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.00808"}}}},{"rank_in_archive_order":126,"model":"NAT-Base","metrics":{"GFLOPs (512 x 512)":"1137","Params (M)":"123","Validation mIoU":"49.7"},"uses_additional_data":false,"paper_date":"2022-04-14","paper":"/paper/neighborhood-attention-transformer","paper_url":"https://arxiv.org/abs/2204.07143v5","paper_title":"Neighborhood Attention Transformer","code":"https://github.com/huggingface/transformers","n_code_links":5,"official":{"repos":["SHI-Labs/Neighborhood-Attention-Transformer","shi-labs/natten"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0,"sample_list":"/paper/neighborhood-attention-transformer#ran","syntology_url":"https://syntology.ai/paper/2204.07143","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.07143"}}}},{"rank_in_archive_order":127,"model":"Swin-B (UperNet, ImageNet-1k pretrain)","metrics":{"Validation mIoU":"49.7"},"uses_additional_data":false,"paper_date":"2021-03-25","paper":"/paper/swin-transformer-hierarchical-vision","paper_url":"https://arxiv.org/abs/2103.14030v2","paper_title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","code":"https://github.com/huggingface/transformers","n_code_links":80,"official":{"repos":["microsoft/Swin-Transformer"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["listed"]},"syntology":{"n_ran":123,"n_constructed":45,"n_ran_checked":79,"n_instrument":44,"n_unverified":84,"n_samples":207,"n_pointer_only_licence":45,"sample_list":"/paper/swin-transformer-hierarchical-vision#ran","syntology_url":"https://syntology.ai/paper/2103.14030","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.14030"}}}},{"rank_in_archive_order":128,"model":"Seg-B/8 (MS, ViT-B)","metrics":{"Validation mIoU":"49.61"},"uses_additional_data":false,"paper_date":"2021-05-12","paper":"/paper/segmenter-transformer-for-semantic","paper_url":"https://arxiv.org/abs/2105.05633v3","paper_title":"Segmenter: Transformer for Semantic Segmentation","code":"https://github.com/PaddlePaddle/PaddleSeg","n_code_links":8,"official":{"repos":["rstrudel/segmenter"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":3,"n_samples":7,"n_pointer_only_licence":0,"sample_list":"/paper/segmenter-transformer-for-semantic#ran","syntology_url":"https://syntology.ai/paper/2105.05633","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.05633"}}}},{"rank_in_archive_order":129,"model":"ConvNeXt-S","metrics":{"GFLOPs (512 x 512)":"1027","Params (M)":"82","Validation mIoU":"49.6"},"uses_additional_data":false,"paper_date":"2022-01-10","paper":"/paper/a-convnet-for-the-2020s","paper_url":"https://arxiv.org/abs/2201.03545v2","paper_title":"A ConvNet for the 2020s","code":"https://github.com/keras-team/keras/blob/master/keras/applications/convnext.py","n_code_links":54,"official":{"repos":["facebookresearch/ConvNeXt"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":57,"n_constructed":39,"n_ran_checked":49,"n_instrument":8,"n_unverified":23,"n_samples":80,"n_pointer_only_licence":12,"sample_list":"/paper/a-convnet-for-the-2020s#ran","syntology_url":"https://syntology.ai/paper/2201.03545","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.03545"}}}},{"rank_in_archive_order":130,"model":"Light-Ham (VAN-Base)","metrics":{"GFLOPs (512 x 512)":"34.4","Params (M)":"27.4","Validation mIoU":"49.6"},"uses_additional_data":false,"paper_date":"2021-09-09","paper":"/paper/is-attention-better-than-matrix-decomposition-1","paper_url":"https://arxiv.org/abs/2109.04553v2","paper_title":"Is Attention Better Than Matrix Decomposition?","code":"https://github.com/Gsunshine/Enjoy-Hamburger","n_code_links":3,"official":{"repos":["Gsunshine/Enjoy-Hamburger"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3,"sample_list":"/paper/is-attention-better-than-matrix-decomposition-1#ran","syntology_url":"https://syntology.ai/paper/2109.04553","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.04553"}}}},{"rank_in_archive_order":131,"model":"NAT-Small","metrics":{"GFLOPs (512 x 512)":"1010","Params (M)":"82","Validation mIoU":"49.5"},"uses_additional_data":false,"paper_date":"2022-04-14","paper":"/paper/neighborhood-attention-transformer","paper_url":"https://arxiv.org/abs/2204.07143v5","paper_title":"Neighborhood Attention Transformer","code":"https://github.com/huggingface/transformers","n_code_links":5,"official":{"repos":["SHI-Labs/Neighborhood-Attention-Transformer","shi-labs/natten"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0,"sample_list":"/paper/neighborhood-attention-transformer#ran","syntology_url":"https://syntology.ai/paper/2204.07143","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.07143"}}}},{"rank_in_archive_order":132,"model":"DaViT-B","metrics":{"Validation mIoU":"49.4"},"uses_additional_data":false,"paper_date":"2022-04-07","paper":"/paper/davit-dual-attention-vision-transformers","paper_url":"https://arxiv.org/abs/2204.03645v1","paper_title":"DaViT: Dual Attention Vision Transformers","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":4,"official":{"repos":["dingmyu/davit"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":5,"n_ran_no_instrument_failure":6,"n_unverified":7,"ran_from_kinds":["official"]},"syntology":{"n_ran":8,"n_constructed":5,"n_ran_checked":6,"n_instrument":2,"n_unverified":7,"n_samples":15,"n_pointer_only_licence":0,"sample_list":"/paper/davit-dual-attention-vision-transformers#ran","syntology_url":"https://syntology.ai/paper/2204.03645","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.03645"}}}},{"rank_in_archive_order":133,"model":"DAT-B (UperNet)","metrics":{"Params (M)":"121","Validation mIoU":"49.38"},"uses_additional_data":false,"paper_date":"2022-01-03","paper":"/paper/vision-transformer-with-deformable-attention","paper_url":"https://arxiv.org/abs/2201.00520v3","paper_title":"Vision Transformer with Deformable Attention","code":"https://github.com/leaplabthu/dat","n_code_links":2,"official":{"repos":["leaplabthu/dat"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":8,"n_constructed":4,"n_ran_checked":4,"n_instrument":4,"n_unverified":2,"n_samples":10,"n_pointer_only_licence":0,"sample_list":"/paper/vision-transformer-with-deformable-attention#ran","syntology_url":"https://syntology.ai/paper/2201.00520","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.00520"}}}},{"rank_in_archive_order":134,"model":"PatchConvNet-S60 (UperNet)","metrics":{"Validation mIoU":"49.3"},"uses_additional_data":false,"paper_date":"2021-12-27","paper":"/paper/augmenting-convolutional-networks-with","paper_url":"https://arxiv.org/abs/2112.13692v1","paper_title":"Augmenting Convolutional networks with attention-based aggregation","code":"https://github.com/facebookresearch/deit","n_code_links":5,"official":{"repos":["facebookresearch/deit"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0,"sample_list":"/paper/augmenting-convolutional-networks-with#ran","syntology_url":"https://syntology.ai/paper/2112.13692","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.13692"}}}},{"rank_in_archive_order":135,"model":"ColorMAE-Green-ViTB-1600","metrics":{"Validation mIoU":"49.3"},"uses_additional_data":false,"paper_date":"2024-07-17","paper":"/paper/colormae-exploring-data-independent-masking","paper_url":"https://arxiv.org/abs/2407.13036v1","paper_title":"ColorMAE: Exploring data-independent masking strategies in Masked AutoEncoders","code":"https://github.com/carlosh93/ColorMAE","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":136,"model":"MogaNet-S (UperNet)","metrics":{"GFLOPs (512 x 512)":"946","Validation mIoU":"49.2"},"uses_additional_data":false,"paper_date":"2022-11-07","paper":"/paper/efficient-multi-order-gated-aggregation","paper_url":"https://arxiv.org/abs/2211.03295v3","paper_title":"MogaNet: Multi-order Gated Aggregation Network","code":"https://github.com/chengtan9907/OpenSTL","n_code_links":7,"official":{"repos":["Westlake-AI/MogaNet","Westlake-AI/openmixup","chengtan9907/OpenSTL"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":7,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]},"syntology":{"n_ran":12,"n_constructed":7,"n_ran_checked":10,"n_instrument":2,"n_unverified":3,"n_samples":15,"n_pointer_only_licence":0,"sample_list":"/paper/efficient-multi-order-gated-aggregation#ran","syntology_url":"https://syntology.ai/paper/2211.03295","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.03295"}}}},{"rank_in_archive_order":137,"model":"Shift-B (UperNet)","metrics":{"Validation mIoU":"49.2"},"uses_additional_data":false,"paper_date":"2022-01-26","paper":"/paper/when-shift-operation-meets-vision-transformer","paper_url":"https://arxiv.org/abs/2201.10801v1","paper_title":"When Shift Operation Meets Vision Transformer: An Extremely Simple Alternative to Attention Mechanism","code":"https://github.com/keras-team/keras-io/blob/master/examples/vision/shiftvit.py","n_code_links":2,"official":{"repos":["microsoft/SPACH"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":6,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":6,"n_constructed":6,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_samples":7,"n_pointer_only_licence":0,"sample_list":"/paper/when-shift-operation-meets-vision-transformer#ran","syntology_url":"https://syntology.ai/paper/2201.10801","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.10801"}}}},{"rank_in_archive_order":138,"model":"UniRepLKNet-T","metrics":{"Validation mIoU":"49.1"},"uses_additional_data":false,"paper_date":"2023-11-27","paper":"/paper/unireplknet-a-universal-perception-large","paper_url":"https://arxiv.org/abs/2311.15599v2","paper_title":"UniRepLKNet: A Universal Perception Large-Kernel ConvNet for Audio, Video, Point Cloud, Time-Series and Image Recognition","code":"https://github.com/ailab-cvc/unireplknet","n_code_links":3,"official":{"repos":["ailab-cvc/unireplknet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_samples":2,"n_pointer_only_licence":0,"sample_list":"/paper/unireplknet-a-universal-perception-large#ran","syntology_url":"https://syntology.ai/paper/2311.15599","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.15599"}}}},{"rank_in_archive_order":139,"model":"DPT-Hybrid","metrics":{"Validation mIoU":"49.02"},"uses_additional_data":false,"paper_date":"2021-03-24","paper":"/paper/vision-transformers-for-dense-prediction","paper_url":"https://arxiv.org/abs/2103.13413v1","paper_title":"Vision Transformers for Dense Prediction","code":"https://github.com/huggingface/transformers","n_code_links":15,"official":null,"syntology":{"n_ran":65,"n_constructed":19,"n_ran_checked":32,"n_instrument":33,"n_unverified":51,"n_samples":116,"n_pointer_only_licence":15,"sample_list":"/paper/vision-transformers-for-dense-prediction#ran","syntology_url":"https://syntology.ai/paper/2103.13413","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.13413"}}}},{"rank_in_archive_order":140,"model":"GC ViT-B","metrics":{"GFLOPs (512 x 512)":"1348","Params (M)":"125","Validation mIoU":"49"},"uses_additional_data":false,"paper_date":"2022-06-20","paper":"/paper/global-context-vision-transformers","paper_url":"https://arxiv.org/abs/2206.09959v5","paper_title":"Global Context Vision Transformers","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":8,"official":{"repos":["nvlabs/gcvit"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":8,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":21,"n_constructed":8,"n_ran_checked":17,"n_instrument":4,"n_unverified":15,"n_samples":36,"n_pointer_only_licence":15,"sample_list":"/paper/global-context-vision-transformers#ran","syntology_url":"https://syntology.ai/paper/2206.09959","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.09959"}}}},{"rank_in_archive_order":141,"model":"A2MIM (ViT-B)","metrics":{"Validation mIoU":"49"},"uses_additional_data":false,"paper_date":"2022-05-27","paper":"/paper/architecture-agnostic-masked-image-modeling","paper_url":"https://arxiv.org/abs/2205.13943v4","paper_title":"Architecture-Agnostic Masked Image Modeling -- From ViT back to CNN","code":"https://github.com/open-mmlab/mmpretrain","n_code_links":3,"official":null,"syntology":null},{"rank_in_archive_order":142,"model":"EfficientViT-B3 (r512)","metrics":{"Validation mIoU":"49"},"uses_additional_data":false,"paper_date":"2022-05-29","paper":"/paper/efficientvit-enhanced-linear-attention-for","paper_url":"https://arxiv.org/abs/2205.14756v6","paper_title":"EfficientViT: Multi-Scale Linear Attention for High-Resolution Dense Prediction","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":6,"official":{"repos":["mit-han-lab/efficientvit","rwightman/pytorch-image-models"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":0,"sample_list":"/paper/efficientvit-enhanced-linear-attention-for#ran","syntology_url":"https://syntology.ai/paper/2205.14756","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.14756"}}}},{"rank_in_archive_order":143,"model":"DiNAT-Tiny (UperNet)","metrics":{"Validation mIoU":"48.8"},"uses_additional_data":false,"paper_date":"2022-09-29","paper":"/paper/dilated-neighborhood-attention-transformer","paper_url":"https://arxiv.org/abs/2209.15001v3","paper_title":"Dilated Neighborhood Attention Transformer","code":"https://github.com/huggingface/transformers","n_code_links":7,"official":null,"syntology":null},{"rank_in_archive_order":144,"model":"HRViT-b2 (SegFormer, SS)","metrics":{"GFLOPs (512 x 512)":"28.0","Params (M)":"20.8","Validation mIoU":"48.76"},"uses_additional_data":false,"paper_date":"2021-11-01","paper":"/paper/hrvit-multi-scale-high-resolution-vision","paper_url":"https://arxiv.org/abs/2111.01236v2","paper_title":"Multi-Scale High-Resolution Vision Transformer for Semantic Segmentation","code":"https://github.com/facebookresearch/HRViT","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":145,"model":"NAT-Tiny","metrics":{"GFLOPs (512 x 512)":"934","Params (M)":"58","Validation mIoU":"48.4"},"uses_additional_data":false,"paper_date":"2022-04-14","paper":"/paper/neighborhood-attention-transformer","paper_url":"https://arxiv.org/abs/2204.07143v5","paper_title":"Neighborhood Attention Transformer","code":"https://github.com/huggingface/transformers","n_code_links":5,"official":{"repos":["SHI-Labs/Neighborhood-Attention-Transformer","shi-labs/natten"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0,"sample_list":"/paper/neighborhood-attention-transformer#ran","syntology_url":"https://syntology.ai/paper/2204.07143","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.07143"}}}},{"rank_in_archive_order":146,"model":"XCiT-M24/8 (UperNet)","metrics":{"Validation mIoU":"48.4"},"uses_additional_data":false,"paper_date":"2021-06-17","paper":"/paper/xcit-cross-covariance-image-transformers","paper_url":"https://arxiv.org/abs/2106.09681v2","paper_title":"XCiT: Cross-Covariance Image Transformers","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":12,"official":{"repos":["facebookresearch/xcit","rwightman/pytorch-image-models"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":4,"n_samples":14,"n_pointer_only_licence":11,"sample_list":"/paper/xcit-cross-covariance-image-transformers#ran","syntology_url":"https://syntology.ai/paper/2106.09681","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.09681"}}}},{"rank_in_archive_order":147,"model":"ResNeSt-200","metrics":{"Validation mIoU":"48.36"},"uses_additional_data":false,"paper_date":"2020-04-19","paper":"/paper/resnest-split-attention-networks","paper_url":"https://arxiv.org/abs/2004.08955v2","paper_title":"ResNeSt: Split-Attention Networks","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":36,"official":{"repos":["zhanghang1989/ResNeSt"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":28,"n_constructed":0,"n_ran_checked":21,"n_instrument":7,"n_unverified":20,"n_samples":48,"n_pointer_only_licence":23,"sample_list":"/paper/resnest-split-attention-networks#ran","syntology_url":"https://syntology.ai/paper/2004.08955","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.08955"}}}},{"rank_in_archive_order":148,"model":"DAT-S (UperNet)","metrics":{"Params (M)":"81","Validation mIoU":"48.31"},"uses_additional_data":false,"paper_date":"2022-01-03","paper":"/paper/vision-transformer-with-deformable-attention","paper_url":"https://arxiv.org/abs/2201.00520v3","paper_title":"Vision Transformer with Deformable Attention","code":"https://github.com/leaplabthu/dat","n_code_links":2,"official":{"repos":["leaplabthu/dat"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":8,"n_constructed":4,"n_ran_checked":4,"n_instrument":4,"n_unverified":2,"n_samples":10,"n_pointer_only_licence":0,"sample_list":"/paper/vision-transformer-with-deformable-attention#ran","syntology_url":"https://syntology.ai/paper/2201.00520","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.00520"}}}},{"rank_in_archive_order":149,"model":"GC ViT-S","metrics":{"GFLOPs (512 x 512)":"1163","Params (M)":"84","Validation mIoU":"48.3"},"uses_additional_data":false,"paper_date":"2022-06-20","paper":"/paper/global-context-vision-transformers","paper_url":"https://arxiv.org/abs/2206.09959v5","paper_title":"Global Context Vision Transformers","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":8,"official":{"repos":["nvlabs/gcvit"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":8,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":21,"n_constructed":8,"n_ran_checked":17,"n_instrument":4,"n_unverified":15,"n_samples":36,"n_pointer_only_licence":15,"sample_list":"/paper/global-context-vision-transformers#ran","syntology_url":"https://syntology.ai/paper/2206.09959","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.09959"}}}},{"rank_in_archive_order":150,"model":"InternImage-T","metrics":{"GFLOPs":"944","Params (M)":"59","Validation mIoU":"48.1"},"uses_additional_data":false,"paper_date":"2022-11-10","paper":"/paper/internimage-exploring-large-scale-vision","paper_url":"https://arxiv.org/abs/2211.05778v4","paper_title":"InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions","code":"https://github.com/opengvlab/internimage","n_code_links":3,"official":{"repos":["opengvlab/internimage"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["listed"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":0,"sample_list":"/paper/internimage-exploring-large-scale-vision#ran","syntology_url":"https://syntology.ai/paper/2211.05778","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.05778"}}}},{"rank_in_archive_order":151,"model":"VAN-Large","metrics":{"Params (M)":"49","Validation mIoU":"48.1"},"uses_additional_data":false,"paper_date":"2022-02-20","paper":"/paper/visual-attention-network","paper_url":"https://arxiv.org/abs/2202.09741v5","paper_title":"Visual Attention Network","code":"https://github.com/huggingface/transformers","n_code_links":21,"official":{"repos":["Visual-Attention-Network/VAN-Classification"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_samples":6,"n_pointer_only_licence":0,"sample_list":"/paper/visual-attention-network#ran","syntology_url":"https://syntology.ai/paper/2202.09741","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.09741"}}}},{"rank_in_archive_order":152,"model":"XCiT-S24/8 (UperNet)","metrics":{"Validation mIoU":"48.1"},"uses_additional_data":false,"paper_date":"2021-06-17","paper":"/paper/xcit-cross-covariance-image-transformers","paper_url":"https://arxiv.org/abs/2106.09681v2","paper_title":"XCiT: Cross-Covariance Image Transformers","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":12,"official":{"repos":["facebookresearch/xcit","rwightman/pytorch-image-models"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":4,"n_samples":14,"n_pointer_only_licence":11,"sample_list":"/paper/xcit-cross-covariance-image-transformers#ran","syntology_url":"https://syntology.ai/paper/2106.09681","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.09681"}}}},{"rank_in_archive_order":153,"model":"MaskFormer(ResNet-101)","metrics":{"Validation mIoU":"48.1"},"uses_additional_data":false,"paper_date":"2021-07-13","paper":"/paper/per-pixel-classification-is-not-all-you-need","paper_url":"https://arxiv.org/abs/2107.06278v2","paper_title":"Per-Pixel Classification is Not All You Need for Semantic Segmentation","code":"https://github.com/huggingface/transformers","n_code_links":3,"official":null,"syntology":null},{"rank_in_archive_order":154,"model":"MAE (ViT-B, UperNet)","metrics":{"Validation mIoU":"48.1"},"uses_additional_data":false,"paper_date":"2021-11-11","paper":"/paper/masked-autoencoders-are-scalable-vision","paper_url":"https://arxiv.org/abs/2111.06377v2","paper_title":"Masked Autoencoders Are Scalable Vision Learners","code":"https://github.com/facebookresearch/mae","n_code_links":58,"official":{"repos":["facebookresearch/mae"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"syntology":{"n_ran":86,"n_constructed":40,"n_ran_checked":68,"n_instrument":18,"n_unverified":51,"n_samples":137,"n_pointer_only_licence":78,"sample_list":"/paper/masked-autoencoders-are-scalable-vision#ran","syntology_url":"https://syntology.ai/paper/2111.06377","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.06377"}}}},{"rank_in_archive_order":155,"model":"HRNetV2 + OCR + RMI (PaddleClas pretrained)","metrics":{"Validation mIoU":"47.98"},"uses_additional_data":false,"paper_date":"2019-09-24","paper":"/paper/object-contextual-representations-for","paper_url":"https://arxiv.org/abs/1909.11065v6","paper_title":"Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation","code":"https://github.com/open-mmlab/mmsegmentation","n_code_links":11,"official":{"repos":["HRNet/HRNet-Semantic-Segmentation"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":4,"n_samples":9,"n_pointer_only_licence":1,"sample_list":"/paper/object-contextual-representations-for#ran","syntology_url":"https://syntology.ai/paper/1909.11065","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.11065"}}}},{"rank_in_archive_order":156,"model":"Shift-B","metrics":{"Validation mIoU":"47.9"},"uses_additional_data":false,"paper_date":"2022-01-26","paper":"/paper/when-shift-operation-meets-vision-transformer","paper_url":"https://arxiv.org/abs/2201.10801v1","paper_title":"When Shift Operation Meets Vision Transformer: An Extremely Simple Alternative to Attention Mechanism","code":"https://github.com/keras-team/keras-io/blob/master/examples/vision/shiftvit.py","n_code_links":2,"official":{"repos":["microsoft/SPACH"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":6,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":6,"n_constructed":6,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_samples":7,"n_pointer_only_licence":0,"sample_list":"/paper/when-shift-operation-meets-vision-transformer#ran","syntology_url":"https://syntology.ai/paper/2201.10801","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.10801"}}}},{"rank_in_archive_order":157,"model":"Shift-S","metrics":{"Validation mIoU":"47.8"},"uses_additional_data":false,"paper_date":"2022-01-26","paper":"/paper/when-shift-operation-meets-vision-transformer","paper_url":"https://arxiv.org/abs/2201.10801v1","paper_title":"When Shift Operation Meets Vision Transformer: An Extremely Simple Alternative to Attention Mechanism","code":"https://github.com/keras-team/keras-io/blob/master/examples/vision/shiftvit.py","n_code_links":2,"official":{"repos":["microsoft/SPACH"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":6,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":6,"n_constructed":6,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_samples":7,"n_pointer_only_licence":0,"sample_list":"/paper/when-shift-operation-meets-vision-transformer#ran","syntology_url":"https://syntology.ai/paper/2201.10801","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.10801"}}}},{"rank_in_archive_order":158,"model":"MogaNet-S (Semantic FPN)","metrics":{"GFLOPs (512 x 512)":"189","Validation mIoU":"47.7"},"uses_additional_data":false,"paper_date":"2022-11-07","paper":"/paper/efficient-multi-order-gated-aggregation","paper_url":"https://arxiv.org/abs/2211.03295v3","paper_title":"MogaNet: Multi-order Gated Aggregation Network","code":"https://github.com/chengtan9907/OpenSTL","n_code_links":7,"official":{"repos":["Westlake-AI/MogaNet","Westlake-AI/openmixup","chengtan9907/OpenSTL"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":7,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]},"syntology":{"n_ran":12,"n_constructed":7,"n_ran_checked":10,"n_instrument":2,"n_unverified":3,"n_samples":15,"n_pointer_only_licence":0,"sample_list":"/paper/efficient-multi-order-gated-aggregation#ran","syntology_url":"https://syntology.ai/paper/2211.03295","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.03295"}}}},{"rank_in_archive_order":159,"model":"SeMask (SeMask Swin-S FPN)","metrics":{"Params (M)":"56","Validation mIoU":"47.63"},"uses_additional_data":false,"paper_date":"2021-12-23","paper":"/paper/semask-semantically-masked-transformers-for-1","paper_url":"https://arxiv.org/abs/2112.12782v3","paper_title":"SeMask: Semantically Masked Transformers for Semantic Segmentation","code":"https://github.com/Picsart-AI-Research/SeMask-Segmentation","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":160,"model":"ResNeSt-269","metrics":{"Validation mIoU":"47.60"},"uses_additional_data":false,"paper_date":"2020-04-19","paper":"/paper/resnest-split-attention-networks","paper_url":"https://arxiv.org/abs/2004.08955v2","paper_title":"ResNeSt: Split-Attention Networks","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":36,"official":{"repos":["zhanghang1989/ResNeSt"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":28,"n_constructed":0,"n_ran_checked":21,"n_instrument":7,"n_unverified":20,"n_samples":48,"n_pointer_only_licence":23,"sample_list":"/paper/resnest-split-attention-networks#ran","syntology_url":"https://syntology.ai/paper/2004.08955","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.08955"}}}},{"rank_in_archive_order":161,"model":"UperNet Shuffle-T","metrics":{"Validation mIoU":"47.6"},"uses_additional_data":false,"paper_date":"2021-06-07","paper":"/paper/shuffle-transformer-rethinking-spatial","paper_url":"https://arxiv.org/abs/2106.03650v1","paper_title":"Shuffle Transformer: Rethinking Spatial Shuffle for Vision Transformer","code":"https://github.com/alibaba/EasyCV","n_code_links":4,"official":null,"syntology":{"n_ran":10,"n_constructed":0,"n_ran_checked":6,"n_instrument":4,"n_unverified":2,"n_samples":12,"n_pointer_only_licence":6,"sample_list":"/paper/shuffle-transformer-rethinking-spatial#ran","syntology_url":"https://syntology.ai/paper/2106.03650","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.03650"}}}},{"rank_in_archive_order":162,"model":"CondNet(ResNest-101)","metrics":{"Validation mIoU":"47.54"},"uses_additional_data":false,"paper_date":"2021-09-21","paper":"/paper/condnet-conditional-classifier-for-scene","paper_url":"https://arxiv.org/abs/2109.10322v1","paper_title":"CondNet: Conditional Classifier for Scene Segmentation","code":"https://github.com/sithu31296/semantic-segmentation","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":163,"model":"tiny-MOAT-3 (IN-1K pretraining, single scale)","metrics":{"Params (M)":"24","Validation mIoU":"47.5"},"uses_additional_data":false,"paper_date":"2022-10-04","paper":"/paper/moat-alternating-mobile-convolution-and","paper_url":"https://arxiv.org/abs/2210.01820v2","paper_title":"MOAT: Alternating Mobile Convolution and Attention Brings Strong Vision Models","code":"https://github.com/google-research/deeplab2","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":164,"model":"CondNet(ResNet-101)","metrics":{"Validation mIoU":"47.38"},"uses_additional_data":false,"paper_date":"2021-09-21","paper":"/paper/condnet-conditional-classifier-for-scene","paper_url":"https://arxiv.org/abs/2109.10322v1","paper_title":"CondNet: Conditional Classifier for Scene Segmentation","code":"https://github.com/sithu31296/semantic-segmentation","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":165,"model":"DiNAT-Mini (UperNet)","metrics":{"Validation mIoU":"47.2"},"uses_additional_data":false,"paper_date":"2022-09-29","paper":"/paper/dilated-neighborhood-attention-transformer","paper_url":"https://arxiv.org/abs/2209.15001v3","paper_title":"Dilated Neighborhood Attention Transformer","code":"https://github.com/huggingface/transformers","n_code_links":7,"official":null,"syntology":null},{"rank_in_archive_order":166,"model":"DCNAS","metrics":{"Validation mIoU":"47.12"},"uses_additional_data":false,"paper_date":"2020-03-26","paper":"/paper/dcnas-densely-connected-neural-architecture","paper_url":"https://arxiv.org/abs/2003.11883v2","paper_title":"DCNAS: Densely Connected Neural Architecture Search for Semantic Image Segmentation","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":167,"model":"XCiT-S24/8 (Semantic-FPN)","metrics":{"Validation mIoU":"47.1"},"uses_additional_data":false,"paper_date":"2021-06-17","paper":"/paper/xcit-cross-covariance-image-transformers","paper_url":"https://arxiv.org/abs/2106.09681v2","paper_title":"XCiT: Cross-Covariance Image Transformers","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":12,"official":{"repos":["facebookresearch/xcit","rwightman/pytorch-image-models"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":4,"n_samples":14,"n_pointer_only_licence":11,"sample_list":"/paper/xcit-cross-covariance-image-transformers#ran","syntology_url":"https://syntology.ai/paper/2106.09681","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.09681"}}}},{"rank_in_archive_order":168,"model":"ResNeSt-101","metrics":{"Validation mIoU":"46.91"},"uses_additional_data":false,"paper_date":"2020-04-19","paper":"/paper/resnest-split-attention-networks","paper_url":"https://arxiv.org/abs/2004.08955v2","paper_title":"ResNeSt: Split-Attention Networks","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":36,"official":{"repos":["zhanghang1989/ResNeSt"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":28,"n_constructed":0,"n_ran_checked":21,"n_instrument":7,"n_unverified":20,"n_samples":48,"n_pointer_only_licence":23,"sample_list":"/paper/resnest-split-attention-networks#ran","syntology_url":"https://syntology.ai/paper/2004.08955","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.08955"}}}},{"rank_in_archive_order":169,"model":"XCiT-M24/8 (Semantic-FPN)","metrics":{"Validation mIoU":"46.9"},"uses_additional_data":false,"paper_date":"2021-06-17","paper":"/paper/xcit-cross-covariance-image-transformers","paper_url":"https://arxiv.org/abs/2106.09681v2","paper_title":"XCiT: Cross-Covariance Image Transformers","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":12,"official":{"repos":["facebookresearch/xcit","rwightman/pytorch-image-models"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":4,"n_samples":14,"n_pointer_only_licence":11,"sample_list":"/paper/xcit-cross-covariance-image-transformers#ran","syntology_url":"https://syntology.ai/paper/2106.09681","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.09681"}}}},{"rank_in_archive_order":170,"model":"HamNet (ResNet-101)","metrics":{"Validation mIoU":"46.8"},"uses_additional_data":false,"paper_date":"2021-09-09","paper":"/paper/is-attention-better-than-matrix-decomposition-1","paper_url":"https://arxiv.org/abs/2109.04553v2","paper_title":"Is Attention Better Than Matrix Decomposition?","code":"https://github.com/Gsunshine/Enjoy-Hamburger","n_code_links":3,"official":{"repos":["Gsunshine/Enjoy-Hamburger"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3,"sample_list":"/paper/is-attention-better-than-matrix-decomposition-1#ran","syntology_url":"https://syntology.ai/paper/2109.04553","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.04553"}}}},{"rank_in_archive_order":171,"model":"Sequential Ensemble (DeepLabv3+)","metrics":{"Validation mIoU":"46.8"},"uses_additional_data":false,"paper_date":"2022-10-08","paper":"/paper/sequential-ensembling-for-semantic","paper_url":"https://arxiv.org/abs/2210.05387v1","paper_title":"Sequential Ensembling for Semantic Segmentation","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":172,"model":"ConvNeXt-T","metrics":{"GFLOPs (512 x 512)":"939","Params (M)":"60","Validation mIoU":"46.7"},"uses_additional_data":false,"paper_date":"2022-01-10","paper":"/paper/a-convnet-for-the-2020s","paper_url":"https://arxiv.org/abs/2201.03545v2","paper_title":"A ConvNet for the 2020s","code":"https://github.com/keras-team/keras/blob/master/keras/applications/convnext.py","n_code_links":54,"official":{"repos":["facebookresearch/ConvNeXt"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":57,"n_constructed":39,"n_ran_checked":49,"n_instrument":8,"n_unverified":23,"n_samples":80,"n_pointer_only_licence":12,"sample_list":"/paper/a-convnet-for-the-2020s#ran","syntology_url":"https://syntology.ai/paper/2201.03545","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.03545"}}}},{"rank_in_archive_order":173,"model":"VAN-Base (Semantic-FPN)","metrics":{"Validation mIoU":"46.7"},"uses_additional_data":false,"paper_date":"2022-02-20","paper":"/paper/visual-attention-network","paper_url":"https://arxiv.org/abs/2202.09741v5","paper_title":"Visual Attention Network","code":"https://github.com/huggingface/transformers","n_code_links":21,"official":{"repos":["Visual-Attention-Network/VAN-Classification"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_samples":6,"n_pointer_only_licence":0,"sample_list":"/paper/visual-attention-network#ran","syntology_url":"https://syntology.ai/paper/2202.09741","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.09741"}}}},{"rank_in_archive_order":174,"model":"XCiT-S12/8 (UperNet)","metrics":{"Validation mIoU":"46.6"},"uses_additional_data":false,"paper_date":"2021-06-17","paper":"/paper/xcit-cross-covariance-image-transformers","paper_url":"https://arxiv.org/abs/2106.09681v2","paper_title":"XCiT: Cross-Covariance Image Transformers","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":12,"official":{"repos":["facebookresearch/xcit","rwightman/pytorch-image-models"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":4,"n_samples":14,"n_pointer_only_licence":11,"sample_list":"/paper/xcit-cross-covariance-image-transformers#ran","syntology_url":"https://syntology.ai/paper/2106.09681","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.09681"}}}},{"rank_in_archive_order":175,"model":"GC ViT-T","metrics":{"GFLOPs (512 x 512)":"947","Params (M)":"58","Validation mIoU":"46.5"},"uses_additional_data":false,"paper_date":"2022-06-20","paper":"/paper/global-context-vision-transformers","paper_url":"https://arxiv.org/abs/2206.09959v5","paper_title":"Global Context Vision Transformers","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":8,"official":{"repos":["nvlabs/gcvit"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":8,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":21,"n_constructed":8,"n_ran_checked":17,"n_instrument":4,"n_unverified":15,"n_samples":36,"n_pointer_only_licence":15,"sample_list":"/paper/global-context-vision-transformers#ran","syntology_url":"https://syntology.ai/paper/2206.09959","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.09959"}}}},{"rank_in_archive_order":176,"model":"NAT-Mini","metrics":{"GFLOPs (512 x 512)":"900","Params (M)":"50","Validation mIoU":"46.4"},"uses_additional_data":false,"paper_date":"2022-04-14","paper":"/paper/neighborhood-attention-transformer","paper_url":"https://arxiv.org/abs/2204.07143v5","paper_title":"Neighborhood Attention Transformer","code":"https://github.com/huggingface/transformers","n_code_links":5,"official":{"repos":["SHI-Labs/Neighborhood-Attention-Transformer","shi-labs/natten"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0,"sample_list":"/paper/neighborhood-attention-transformer#ran","syntology_url":"https://syntology.ai/paper/2204.07143","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.07143"}}}},{"rank_in_archive_order":177,"model":"Shift-T","metrics":{"Validation mIoU":"46.3"},"uses_additional_data":false,"paper_date":"2022-01-26","paper":"/paper/when-shift-operation-meets-vision-transformer","paper_url":"https://arxiv.org/abs/2201.10801v1","paper_title":"When Shift Operation Meets Vision Transformer: An Extremely Simple Alternative to Attention Mechanism","code":"https://github.com/keras-team/keras-io/blob/master/examples/vision/shiftvit.py","n_code_links":2,"official":{"repos":["microsoft/SPACH"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":6,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":6,"n_constructed":6,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_samples":7,"n_pointer_only_licence":0,"sample_list":"/paper/when-shift-operation-meets-vision-transformer#ran","syntology_url":"https://syntology.ai/paper/2201.10801","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.10801"}}}},{"rank_in_archive_order":178,"model":"DaViT-T","metrics":{"Validation mIoU":"46.3"},"uses_additional_data":false,"paper_date":"2022-04-07","paper":"/paper/davit-dual-attention-vision-transformers","paper_url":"https://arxiv.org/abs/2204.03645v1","paper_title":"DaViT: Dual Attention Vision Transformers","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":4,"official":{"repos":["dingmyu/davit"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":5,"n_ran_no_instrument_failure":6,"n_unverified":7,"ran_from_kinds":["official"]},"syntology":{"n_ran":8,"n_constructed":5,"n_ran_checked":6,"n_instrument":2,"n_unverified":7,"n_samples":15,"n_pointer_only_licence":0,"sample_list":"/paper/davit-dual-attention-vision-transformers#ran","syntology_url":"https://syntology.ai/paper/2204.03645","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.03645"}}}},{"rank_in_archive_order":179,"model":"CPN(ResNet-101)","metrics":{"Validation mIoU":"46.27"},"uses_additional_data":false,"paper_date":"2020-04-03","paper":"/paper/context-prior-for-scene-segmentation","paper_url":"https://arxiv.org/abs/2004.01547v1","paper_title":"Context Prior for Scene Segmentation","code":"https://github.com/ycszen/ContextPrior","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":180,"model":"MultiMAE (ViT-B)","metrics":{"Validation mIoU":"46.2"},"uses_additional_data":false,"paper_date":"2022-04-04","paper":"/paper/multimae-multi-modal-multi-task-masked","paper_url":"https://arxiv.org/abs/2204.01678v1","paper_title":"MultiMAE: Multi-modal Multi-task Masked Autoencoders","code":"https://github.com/EPFL-VILAB/MultiMAE","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":181,"model":"DRAN(ResNet-101)","metrics":{"Validation mIoU":"46.18"},"uses_additional_data":false,"paper_date":"2020-08-05","paper":"/paper/scene-segmentation-with-dual-relation-aware","paper_url":"https://ieeexplore.ieee.org/document/9154612","paper_title":"Scene Segmentation with Dual Relation-aware Attention Network","code":"https://github.com/junfu1115/DRAN","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":182,"model":"PyConvSegNet-152","metrics":{"Test Score":"56.52","Validation mIoU":"45.99"},"uses_additional_data":false,"paper_date":"2020-06-20","paper":"/paper/pyramidal-convolution-rethinking","paper_url":"https://arxiv.org/abs/2006.11538v1","paper_title":"Pyramidal Convolution: Rethinking Convolutional Neural Networks for Visual Recognition","code":"https://github.com/iduta/pyconv","n_code_links":3,"official":null,"syntology":null},{"rank_in_archive_order":183,"model":"DNL","metrics":{"Validation mIoU":"45.97"},"uses_additional_data":false,"paper_date":"2020-06-11","paper":"/paper/disentangled-non-local-neural-networks","paper_url":"https://arxiv.org/abs/2006.06668v2","paper_title":"Disentangled Non-Local Neural Networks","code":"https://github.com/open-mmlab/mmsegmentation","n_code_links":5,"official":{"repos":["Howal/DNL-Object-Detection","yinmh17/DNL-Semantic-Segmentation"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":0,"sample_list":"/paper/disentangled-non-local-neural-networks#ran","syntology_url":"https://syntology.ai/paper/2006.06668","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.06668"}}}},{"rank_in_archive_order":184,"model":"ACNet (ResNet-101)","metrics":{"Validation mIoU":"45.90"},"uses_additional_data":false,"paper_date":"2019-11-05","paper":"/paper/adaptive-context-network-for-scene-parsing-1","paper_url":"https://arxiv.org/abs/1911.01664v1","paper_title":"Adaptive Context Network for Scene Parsing","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":185,"model":"ACNet\n(ResNet-101)","metrics":{"Validation mIoU":"45.90"},"uses_additional_data":false,"paper_date":"2019-11-05","paper":"/paper/adaptive-context-network-for-scene-parsing-1","paper_url":"https://arxiv.org/abs/1911.01664v1","paper_title":"Adaptive Context Network for Scene Parsing","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":186,"model":"HRViT-b1 (SegFormer, SS)","metrics":{"GFLOPs (512 x 512)":"14.6","Params (M)":"8.2","Validation mIoU":"45.88"},"uses_additional_data":false,"paper_date":"2021-11-01","paper":"/paper/hrvit-multi-scale-high-resolution-vision","paper_url":"https://arxiv.org/abs/2111.01236v2","paper_title":"Multi-Scale High-Resolution Vision Transformer for Semantic Segmentation","code":"https://github.com/facebookresearch/HRViT","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":187,"model":"OCR(HRNetV2-W48)","metrics":{"Validation mIoU":"45.66"},"uses_additional_data":false,"paper_date":"2019-09-24","paper":"/paper/object-contextual-representations-for","paper_url":"https://arxiv.org/abs/1909.11065v6","paper_title":"Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation","code":"https://github.com/open-mmlab/mmsegmentation","n_code_links":11,"official":{"repos":["HRNet/HRNet-Semantic-Segmentation"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":4,"n_samples":9,"n_pointer_only_licence":1,"sample_list":"/paper/object-contextual-representations-for#ran","syntology_url":"https://syntology.ai/paper/1909.11065","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.11065"}}}},{"rank_in_archive_order":188,"model":"SPNet (ResNet-101)","metrics":{"Validation mIoU":"45.6"},"uses_additional_data":false,"paper_date":"2020-03-30","paper":"/paper/2003-13328","paper_url":"https://arxiv.org/abs/2003.13328v1","paper_title":"Strip Pooling: Rethinking Spatial Pooling for Scene Parsing","code":"https://github.com/Andrew-Qibin/SPNet","n_code_links":2,"official":{"repos":["Andrew-Qibin/SPNet"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]},"syntology":{"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":4,"n_samples":11,"n_pointer_only_licence":3,"sample_list":"/paper/2003-13328#ran","syntology_url":"https://syntology.ai/paper/2003.13328","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.13328"}}}},{"rank_in_archive_order":189,"model":"Swin-T (UPerNet) MoBY","metrics":{"Validation mIoU":"45.58"},"uses_additional_data":false,"paper_date":"2021-05-10","paper":"/paper/self-supervised-learning-with-swin","paper_url":"https://arxiv.org/abs/2105.04553v2","paper_title":"Self-Supervised Learning with Swin Transformers","code":"https://github.com/microsoft/Swin-Transformer","n_code_links":6,"official":null,"syntology":null},{"rank_in_archive_order":190,"model":"DAT-T (UperNet)","metrics":{"Params (M)":"60","Validation mIoU":"45.54"},"uses_additional_data":false,"paper_date":"2022-01-03","paper":"/paper/vision-transformer-with-deformable-attention","paper_url":"https://arxiv.org/abs/2201.00520v3","paper_title":"Vision Transformer with Deformable Attention","code":"https://github.com/leaplabthu/dat","n_code_links":2,"official":{"repos":["leaplabthu/dat"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":8,"n_constructed":4,"n_ran_checked":4,"n_instrument":4,"n_unverified":2,"n_samples":10,"n_pointer_only_licence":0,"sample_list":"/paper/vision-transformer-with-deformable-attention#ran","syntology_url":"https://syntology.ai/paper/2201.00520","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.00520"}}}},{"rank_in_archive_order":191,"model":"iBOT (ViT-S/16)","metrics":{"Validation mIoU":"45.4"},"uses_additional_data":false,"paper_date":"2021-11-15","paper":"/paper/ibot-image-bert-pre-training-with-online","paper_url":"https://arxiv.org/abs/2111.07832v3","paper_title":"iBOT: Image BERT Pre-Training with Online Tokenizer","code":"https://github.com/bytedance/ibot","n_code_links":2,"official":{"repos":["bytedance/ibot"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]},"syntology":{"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0,"sample_list":"/paper/ibot-image-bert-pre-training-with-online#ran","syntology_url":"https://syntology.ai/paper/2111.07832","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.07832"}}}},{"rank_in_archive_order":192,"model":"EANet\n(ResNet-101)","metrics":{"Validation mIoU":"45.33"},"uses_additional_data":false,"paper_date":"2021-05-05","paper":"/paper/beyond-self-attention-external-attention","paper_url":"https://arxiv.org/abs/2105.02358v2","paper_title":"Beyond Self-attention: External Attention using Two Linear Layers for Visual Tasks","code":"https://github.com/xmu-xiaoma666/External-Attention-pytorch","n_code_links":7,"official":null,"syntology":null},{"rank_in_archive_order":193,"model":"OCR (ResNet-101)","metrics":{"Validation mIoU":"45.28"},"uses_additional_data":false,"paper_date":"2019-09-24","paper":"/paper/object-contextual-representations-for","paper_url":"https://arxiv.org/abs/1909.11065v6","paper_title":"Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation","code":"https://github.com/open-mmlab/mmsegmentation","n_code_links":11,"official":{"repos":["HRNet/HRNet-Semantic-Segmentation"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":4,"n_samples":9,"n_pointer_only_licence":1,"sample_list":"/paper/object-contextual-representations-for#ran","syntology_url":"https://syntology.ai/paper/1909.11065","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.11065"}}}},{"rank_in_archive_order":194,"model":"Asymmetric ALNN","metrics":{"Validation mIoU":"45.24"},"uses_additional_data":false,"paper_date":"2019-08-21","paper":"/paper/asymmetric-non-local-neural-networks-for","paper_url":"https://arxiv.org/abs/1908.07678v5","paper_title":"Asymmetric Non-local Neural Networks for Semantic Segmentation","code":"https://github.com/open-mmlab/mmsegmentation","n_code_links":5,"official":{"repos":["MendelXu/ANN","donnyyou/torchcv"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":0,"sample_list":"/paper/asymmetric-non-local-neural-networks-for#ran","syntology_url":"https://syntology.ai/paper/1908.07678","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.07678"}}}},{"rank_in_archive_order":195,"model":"Light-Ham (VAN-Small, D=256)","metrics":{"GFLOPs (512 x 512)":"15.8","Params (M)":"13.8","Validation mIoU":"45.2"},"uses_additional_data":false,"paper_date":"2021-09-09","paper":"/paper/is-attention-better-than-matrix-decomposition-1","paper_url":"https://arxiv.org/abs/2109.04553v2","paper_title":"Is Attention Better Than Matrix Decomposition?","code":"https://github.com/Gsunshine/Enjoy-Hamburger","n_code_links":3,"official":{"repos":["Gsunshine/Enjoy-Hamburger"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3,"sample_list":"/paper/is-attention-better-than-matrix-decomposition-1#ran","syntology_url":"https://syntology.ai/paper/2109.04553","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.04553"}}}},{"rank_in_archive_order":196,"model":"LaU-regression-loss","metrics":{"Test Score":"56.32","Validation mIoU":"45.02"},"uses_additional_data":false,"paper_date":"2019-11-13","paper":"/paper/location-aware-upsampling-for-semantic","paper_url":"https://arxiv.org/abs/1911.05250v2","paper_title":"Location-aware Upsampling for Semantic Segmentation","code":"https://github.com/HolmesShuan/Location-aware-Upsampling-for-Semantic-Segmentation","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":197,"model":"PSPNet","metrics":{"Test Score":"55.38","Validation mIoU":"44.94"},"uses_additional_data":false,"paper_date":"2016-12-04","paper":"/paper/pyramid-scene-parsing-network","paper_url":"http://arxiv.org/abs/1612.01105v2","paper_title":"Pyramid Scene Parsing Network","code":"https://github.com/tensorflow/models","n_code_links":67,"official":{"repos":["hszhao/PSPNet"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":21,"n_constructed":0,"n_ran_checked":14,"n_instrument":7,"n_unverified":8,"n_samples":29,"n_pointer_only_licence":5,"sample_list":"/paper/pyramid-scene-parsing-network#ran","syntology_url":"https://syntology.ai/paper/1612.01105","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1612.01105"}}}},{"rank_in_archive_order":198,"model":"tiny-MOAT-2 (IN-1K pretraining, single scale)","metrics":{"Params (M)":"13","Validation mIoU":"44.9"},"uses_additional_data":false,"paper_date":"2022-10-04","paper":"/paper/moat-alternating-mobile-convolution-and","paper_url":"https://arxiv.org/abs/2210.01820v2","paper_title":"MOAT: Alternating Mobile Convolution and Attention Brings Strong Vision Models","code":"https://github.com/google-research/deeplab2","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":199,"model":"CFNet(ResNet-101)","metrics":{"Validation mIoU":"44.89"},"uses_additional_data":false,"paper_date":"2019-06-01","paper":"/paper/co-occurrent-features-in-semantic","paper_url":"http://openaccess.thecvf.com/content_CVPR_2019/html/Zhang_Co-Occurrent_Features_in_Semantic_Segmentation_CVPR_2019_paper.html","paper_title":"Co-Occurrent Features in Semantic Segmentation","code":"https://github.com/zhanghang1989/PyTorch-Encoding","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":200,"model":"EncNet","metrics":{"Test Score":"55.67","Validation mIoU":"44.65"},"uses_additional_data":false,"paper_date":"2018-03-23","paper":"/paper/context-encoding-for-semantic-segmentation","paper_url":"http://arxiv.org/abs/1803.08904v1","paper_title":"Context Encoding for Semantic Segmentation","code":"https://github.com/open-mmlab/mmsegmentation","n_code_links":12,"official":{"repos":["zhanghang1989/PyTorch-Encoding"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":2,"n_samples":8,"n_pointer_only_licence":7,"sample_list":"/paper/context-encoding-for-semantic-segmentation#ran","syntology_url":"https://syntology.ai/paper/1803.08904","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.08904"}}}},{"rank_in_archive_order":201,"model":"LaU-offset-loss","metrics":{"Test Score":"56.41","Validation mIoU":"44.55"},"uses_additional_data":false,"paper_date":"2019-11-13","paper":"/paper/location-aware-upsampling-for-semantic","paper_url":"https://arxiv.org/abs/1911.05250v2","paper_title":"Location-aware Upsampling for Semantic Segmentation","code":"https://github.com/HolmesShuan/Location-aware-Upsampling-for-Semantic-Segmentation","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":202,"model":"EncNet + JPU","metrics":{"Test Score":"55.84","Validation mIoU":"44.34"},"uses_additional_data":false,"paper_date":"2019-03-28","paper":"/paper/fastfcn-rethinking-dilated-convolution-in-the","paper_url":"http://arxiv.org/abs/1903.11816v1","paper_title":"FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation","code":"https://github.com/PaddlePaddle/PaddleSeg","n_code_links":12,"official":null,"syntology":null},{"rank_in_archive_order":203,"model":"SGR (ResNet-101)","metrics":{"Validation mIoU":"44.32"},"uses_additional_data":false,"paper_date":"2018-12-01","paper":"/paper/symbolic-graph-reasoning-meets-convolutions","paper_url":"http://papers.nips.cc/paper/7456-symbolic-graph-reasoning-meets-convolutions","paper_title":"Symbolic Graph Reasoning Meets Convolutions","code":"https://github.com/julianschoep/SGRLayer","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":204,"model":"XCiT-S12/8 (Semantic-FPN)","metrics":{"Validation mIoU":"44.2"},"uses_additional_data":false,"paper_date":"2021-06-17","paper":"/paper/xcit-cross-covariance-image-transformers","paper_url":"https://arxiv.org/abs/2106.09681v2","paper_title":"XCiT: Cross-Covariance Image Transformers","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":12,"official":{"repos":["facebookresearch/xcit","rwightman/pytorch-image-models"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":4,"n_samples":14,"n_pointer_only_licence":11,"sample_list":"/paper/xcit-cross-covariance-image-transformers#ran","syntology_url":"https://syntology.ai/paper/2106.09681","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.09681"}}}},{"rank_in_archive_order":205,"model":"Auto-DeepLab-L","metrics":{"Validation mIoU":"43.98"},"uses_additional_data":false,"paper_date":"2019-01-10","paper":"/paper/auto-deeplab-hierarchical-neural-architecture","paper_url":"http://arxiv.org/abs/1901.02985v2","paper_title":"Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation","code":"https://github.com/tensorflow/models","n_code_links":12,"official":{"repos":["tensorflow/models"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":1,"sample_list":"/paper/auto-deeplab-hierarchical-neural-architecture#ran","syntology_url":"https://syntology.ai/paper/1901.02985","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.02985"}}}},{"rank_in_archive_order":206,"model":"PSANet (ResNet-101)","metrics":{"Validation mIoU":"43.77"},"uses_additional_data":false,"paper_date":"2018-09-01","paper":"/paper/psanet-point-wise-spatial-attention-network","paper_url":"http://openaccess.thecvf.com/content_ECCV_2018/html/Hengshuang_Zhao_PSANet_Point-wise_Spatial_ECCV_2018_paper.html","paper_title":"PSANet: Point-wise Spatial Attention Network for Scene Parsing","code":"https://github.com/open-mmlab/mmsegmentation","n_code_links":4,"official":null,"syntology":null},{"rank_in_archive_order":207,"model":"DSSPN (ResNet-101)","metrics":{"Validation mIoU":"43.68"},"uses_additional_data":false,"paper_date":"2018-03-16","paper":"/paper/dynamic-structured-semantic-propagation","paper_url":"http://arxiv.org/abs/1803.06067v1","paper_title":"Dynamic-structured Semantic Propagation Network","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":208,"model":"PSPNet (ResNet-152)","metrics":{"Validation mIoU":"43.51"},"uses_additional_data":false,"paper_date":"2016-12-04","paper":"/paper/pyramid-scene-parsing-network","paper_url":"http://arxiv.org/abs/1612.01105v2","paper_title":"Pyramid Scene Parsing Network","code":"https://github.com/tensorflow/models","n_code_links":67,"official":{"repos":["hszhao/PSPNet"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":21,"n_constructed":0,"n_ran_checked":14,"n_instrument":7,"n_unverified":8,"n_samples":29,"n_pointer_only_licence":5,"sample_list":"/paper/pyramid-scene-parsing-network#ran","syntology_url":"https://syntology.ai/paper/1612.01105","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1612.01105"}}}},{"rank_in_archive_order":209,"model":"PSPNet\n(ResNet-101)","metrics":{"Validation mIoU":"43.29"},"uses_additional_data":false,"paper_date":"2016-12-04","paper":"/paper/pyramid-scene-parsing-network","paper_url":"http://arxiv.org/abs/1612.01105v2","paper_title":"Pyramid Scene Parsing Network","code":"https://github.com/tensorflow/models","n_code_links":67,"official":{"repos":["hszhao/PSPNet"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":21,"n_constructed":0,"n_ran_checked":14,"n_instrument":7,"n_unverified":8,"n_samples":29,"n_pointer_only_licence":5,"sample_list":"/paper/pyramid-scene-parsing-network#ran","syntology_url":"https://syntology.ai/paper/1612.01105","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1612.01105"}}}},{"rank_in_archive_order":210,"model":"HRNetV2","metrics":{"Validation mIoU":"43.2"},"uses_additional_data":false,"paper_date":"2019-04-09","paper":"/paper/high-resolution-representations-for-labeling","paper_url":"http://arxiv.org/abs/1904.04514v1","paper_title":"High-Resolution Representations for Labeling Pixels and Regions","code":"https://github.com/PaddlePaddle/PaddleDetection","n_code_links":39,"official":{"repos":["leoxiaobin/deep-high-resolution-net.pytorch"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]},"syntology":{"n_ran":14,"n_constructed":0,"n_ran_checked":8,"n_instrument":6,"n_unverified":4,"n_samples":18,"n_pointer_only_licence":11,"sample_list":"/paper/high-resolution-representations-for-labeling#ran","syntology_url":"https://syntology.ai/paper/1904.04514","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.04514"}}}},{"rank_in_archive_order":211,"model":"SeMask (SeMask Swin-T FPN)","metrics":{"Params (M)":"35","Validation mIoU":"43.16"},"uses_additional_data":false,"paper_date":"2021-12-23","paper":"/paper/semask-semantically-masked-transformers-for-1","paper_url":"https://arxiv.org/abs/2112.12782v3","paper_title":"SeMask: Semantically Masked Transformers for Semantic Segmentation","code":"https://github.com/Picsart-AI-Research/SeMask-Segmentation","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":212,"model":"tiny-MOAT-1 (IN-1K pretraining, single scale)","metrics":{"Params (M)":"8","Validation mIoU":"43.1"},"uses_additional_data":false,"paper_date":"2022-10-04","paper":"/paper/moat-alternating-mobile-convolution-and","paper_url":"https://arxiv.org/abs/2210.01820v2","paper_title":"MOAT: Alternating Mobile Convolution and Attention Brings Strong Vision Models","code":"https://github.com/google-research/deeplab2","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":213,"model":"VAN-Small","metrics":{"Params (M)":"18","Validation mIoU":"42.9"},"uses_additional_data":false,"paper_date":"2022-02-20","paper":"/paper/visual-attention-network","paper_url":"https://arxiv.org/abs/2202.09741v5","paper_title":"Visual Attention Network","code":"https://github.com/huggingface/transformers","n_code_links":21,"official":{"repos":["Visual-Attention-Network/VAN-Classification"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_samples":6,"n_pointer_only_licence":0,"sample_list":"/paper/visual-attention-network#ran","syntology_url":"https://syntology.ai/paper/2202.09741","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.09741"}}}},{"rank_in_archive_order":214,"model":"PoolFormer-M48","metrics":{"Validation mIoU":"42.7"},"uses_additional_data":false,"paper_date":"2021-11-22","paper":"/paper/metaformer-is-actually-what-you-need-for","paper_url":"https://arxiv.org/abs/2111.11418v3","paper_title":"MetaFormer Is Actually What You Need for Vision","code":"https://github.com/huggingface/transformers","n_code_links":18,"official":{"repos":["rwightman/pytorch-image-models","sail-sg/poolformer"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":1,"sample_list":"/paper/metaformer-is-actually-what-you-need-for#ran","syntology_url":"https://syntology.ai/paper/2111.11418","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.11418"}}}},{"rank_in_archive_order":215,"model":"UperNet (ResNet-101)","metrics":{"Validation mIoU":"42.66"},"uses_additional_data":false,"paper_date":"2018-07-26","paper":"/paper/unified-perceptual-parsing-for-scene","paper_url":"http://arxiv.org/abs/1807.10221v1","paper_title":"Unified Perceptual Parsing for Scene Understanding","code":"https://github.com/open-mmlab/mmsegmentation","n_code_links":25,"official":{"repos":["CSAILVision/unifiedparsing"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":25,"n_constructed":0,"n_ran_checked":14,"n_instrument":11,"n_unverified":3,"n_samples":28,"n_pointer_only_licence":10,"sample_list":"/paper/unified-perceptual-parsing-for-scene#ran","syntology_url":"https://syntology.ai/paper/1807.10221","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1807.10221"}}}},{"rank_in_archive_order":216,"model":"tiny-MOAT-0 (IN-1K pretraining, single scale)","metrics":{"Params (M)":"6","Validation mIoU":"41.2"},"uses_additional_data":false,"paper_date":"2022-10-04","paper":"/paper/moat-alternating-mobile-convolution-and","paper_url":"https://arxiv.org/abs/2210.01820v2","paper_title":"MOAT: Alternating Mobile Convolution and Attention Brings Strong Vision Models","code":"https://github.com/google-research/deeplab2","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":217,"model":"RefineNet","metrics":{"Validation mIoU":"40.7"},"uses_additional_data":false,"paper_date":"2016-11-20","paper":"/paper/refinenet-multi-path-refinement-networks-for","paper_url":"http://arxiv.org/abs/1611.06612v3","paper_title":"RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation","code":"https://github.com/guosheng/refinenet","n_code_links":13,"official":{"repos":["guosheng/refinenet"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_samples":7,"n_pointer_only_licence":1,"sample_list":"/paper/refinenet-multi-path-refinement-networks-for#ran","syntology_url":"https://syntology.ai/paper/1611.06612","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1611.06612"}}}},{"rank_in_archive_order":218,"model":"FBNetV5","metrics":{"Validation mIoU":"40.4"},"uses_additional_data":false,"paper_date":"2021-11-19","paper":"/paper/fbnetv5-neural-architecture-search-for","paper_url":"https://arxiv.org/abs/2111.10007v3","paper_title":"FBNetV5: Neural Architecture Search for Multiple Tasks in One Run","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":219,"model":"ConvMLP-L","metrics":{"Validation mIoU":"40"},"uses_additional_data":false,"paper_date":"2021-09-09","paper":"/paper/convmlp-hierarchical-convolutional-mlps-for","paper_url":"https://arxiv.org/abs/2109.04454v2","paper_title":"ConvMLP: Hierarchical Convolutional MLPs for Vision","code":"https://github.com/BR-IDL/PaddleViT/tree/develop/image_classification","n_code_links":4,"official":{"repos":["SHI-Labs/Convolutional-MLPs"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]},"syntology":{"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_samples":3,"n_pointer_only_licence":0,"sample_list":"/paper/convmlp-hierarchical-convolutional-mlps-for#ran","syntology_url":"https://syntology.ai/paper/2109.04454","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.04454"}}}},{"rank_in_archive_order":220,"model":"ConvMLP-M","metrics":{"Validation mIoU":"38.6"},"uses_additional_data":false,"paper_date":"2021-09-09","paper":"/paper/convmlp-hierarchical-convolutional-mlps-for","paper_url":"https://arxiv.org/abs/2109.04454v2","paper_title":"ConvMLP: Hierarchical Convolutional MLPs for Vision","code":"https://github.com/BR-IDL/PaddleViT/tree/develop/image_classification","n_code_links":4,"official":{"repos":["SHI-Labs/Convolutional-MLPs"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]},"syntology":{"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_samples":3,"n_pointer_only_licence":0,"sample_list":"/paper/convmlp-hierarchical-convolutional-mlps-for#ran","syntology_url":"https://syntology.ai/paper/2109.04454","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.04454"}}}},{"rank_in_archive_order":221,"model":"VAN-Tiny","metrics":{"Params (M)":"8","Validation mIoU":"38.5"},"uses_additional_data":false,"paper_date":"2022-02-20","paper":"/paper/visual-attention-network","paper_url":"https://arxiv.org/abs/2202.09741v5","paper_title":"Visual Attention Network","code":"https://github.com/huggingface/transformers","n_code_links":21,"official":{"repos":["Visual-Attention-Network/VAN-Classification"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_samples":6,"n_pointer_only_licence":0,"sample_list":"/paper/visual-attention-network#ran","syntology_url":"https://syntology.ai/paper/2202.09741","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.09741"}}}},{"rank_in_archive_order":222,"model":"A2MIM (ResNet-50)","metrics":{"Validation mIoU":"38.3"},"uses_additional_data":false,"paper_date":"2022-05-27","paper":"/paper/architecture-agnostic-masked-image-modeling","paper_url":"https://arxiv.org/abs/2205.13943v4","paper_title":"Architecture-Agnostic Masked Image Modeling -- From ViT back to CNN","code":"https://github.com/open-mmlab/mmpretrain","n_code_links":3,"official":null,"syntology":null},{"rank_in_archive_order":223,"model":"iBOT (ViT-B/16) (linear head)","metrics":{"Validation mIoU":"38.3"},"uses_additional_data":false,"paper_date":"2021-11-15","paper":"/paper/ibot-image-bert-pre-training-with-online","paper_url":"https://arxiv.org/abs/2111.07832v3","paper_title":"iBOT: Image BERT Pre-Training with Online Tokenizer","code":"https://github.com/bytedance/ibot","n_code_links":2,"official":{"repos":["bytedance/ibot"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]},"syntology":{"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0,"sample_list":"/paper/ibot-image-bert-pre-training-with-online#ran","syntology_url":"https://syntology.ai/paper/2111.07832","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.07832"}}}},{"rank_in_archive_order":224,"model":"SegFormer-B0","metrics":{"Params (M)":"3.8","Validation mIoU":"37.4"},"uses_additional_data":true,"paper_date":"2021-05-31","paper":"/paper/segformer-simple-and-efficient-design-for","paper_url":"https://arxiv.org/abs/2105.15203v3","paper_title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","code":"https://github.com/huggingface/transformers","n_code_links":28,"official":{"repos":["NVlabs/SegFormer"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["community","listed","unlocated"]},"syntology":{"n_ran":66,"n_constructed":22,"n_ran_checked":52,"n_instrument":14,"n_unverified":20,"n_samples":86,"n_pointer_only_licence":20,"sample_list":"/paper/segformer-simple-and-efficient-design-for#ran","syntology_url":"https://syntology.ai/paper/2105.15203","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.15203"}}}},{"rank_in_archive_order":225,"model":"MUXNet-m + PPM","metrics":{"Validation mIoU":"35.8"},"uses_additional_data":false,"paper_date":"2020-03-31","paper":"/paper/muxconv-information-multiplexing-in","paper_url":"https://arxiv.org/abs/2003.13880v2","paper_title":"MUXConv: Information Multiplexing in Convolutional Neural Networks","code":"https://github.com/human-analysis/MUXConv","n_code_links":1,"official":{"repos":["human-analysis/MUXConv"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":2,"n_samples":5,"n_pointer_only_licence":5,"sample_list":"/paper/muxconv-information-multiplexing-in#ran","syntology_url":"https://syntology.ai/paper/2003.13880","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.13880"}}}},{"rank_in_archive_order":226,"model":"ConvMLP-S","metrics":{"Validation mIoU":"35.8"},"uses_additional_data":false,"paper_date":"2021-09-09","paper":"/paper/convmlp-hierarchical-convolutional-mlps-for","paper_url":"https://arxiv.org/abs/2109.04454v2","paper_title":"ConvMLP: Hierarchical Convolutional MLPs for Vision","code":"https://github.com/BR-IDL/PaddleViT/tree/develop/image_classification","n_code_links":4,"official":{"repos":["SHI-Labs/Convolutional-MLPs"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]},"syntology":{"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_samples":3,"n_pointer_only_licence":0,"sample_list":"/paper/convmlp-hierarchical-convolutional-mlps-for#ran","syntology_url":"https://syntology.ai/paper/2109.04454","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.04454"}}}},{"rank_in_archive_order":227,"model":"MUXNet-m + C1","metrics":{"Validation mIoU":"32.42"},"uses_additional_data":false,"paper_date":"2020-03-31","paper":"/paper/muxconv-information-multiplexing-in","paper_url":"https://arxiv.org/abs/2003.13880v2","paper_title":"MUXConv: Information Multiplexing in Convolutional Neural Networks","code":"https://github.com/human-analysis/MUXConv","n_code_links":1,"official":{"repos":["human-analysis/MUXConv"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":2,"n_samples":5,"n_pointer_only_licence":5,"sample_list":"/paper/muxconv-information-multiplexing-in#ran","syntology_url":"https://syntology.ai/paper/2003.13880","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.13880"}}}},{"rank_in_archive_order":228,"model":"DilatedNet","metrics":{"Validation mIoU":"32.31"},"uses_additional_data":false,"paper_date":"2015-11-23","paper":"/paper/multi-scale-context-aggregation-by-dilated","paper_url":"http://arxiv.org/abs/1511.07122v3","paper_title":"Multi-Scale Context Aggregation by Dilated Convolutions","code":"https://github.com/fyu/dilation","n_code_links":9,"official":{"repos":["fyu/dilation"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":2,"n_samples":8,"n_pointer_only_licence":2,"sample_list":"/paper/multi-scale-context-aggregation-by-dilated#ran","syntology_url":"https://syntology.ai/paper/1511.07122","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1511.07122"}}}},{"rank_in_archive_order":229,"model":"FCN","metrics":{"Validation mIoU":"29.39"},"uses_additional_data":true,"paper_date":"2014-11-14","paper":"/paper/fully-convolutional-networks-for-semantic-1","paper_url":"http://arxiv.org/abs/1411.4038v2","paper_title":"Fully Convolutional Networks for Semantic Segmentation","code":"https://github.com/pochih/fcn-pytorch","n_code_links":51,"official":null,"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":4,"sample_list":"/paper/fully-convolutional-networks-for-semantic-1#ran","syntology_url":"https://syntology.ai/paper/1411.4038","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1411.4038"}}}},{"rank_in_archive_order":230,"model":"SegNet","metrics":{"Validation mIoU":"21.64"},"uses_additional_data":false,"paper_date":"2015-11-02","paper":"/paper/segnet-a-deep-convolutional-encoder-decoder","paper_url":"http://arxiv.org/abs/1511.00561v3","paper_title":"SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation","code":"https://github.com/PaddlePaddle/PaddleSeg","n_code_links":74,"official":null,"syntology":{"n_ran":22,"n_constructed":0,"n_ran_checked":14,"n_instrument":8,"n_unverified":22,"n_samples":44,"n_pointer_only_licence":11,"sample_list":"/paper/segnet-a-deep-convolutional-encoder-decoder#ran","syntology_url":"https://syntology.ai/paper/1511.00561","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1511.00561"}}}},{"rank_in_archive_order":231,"model":"InternImage-H (M3I Pre-training)","metrics":{"Params (M)":"1310"},"uses_additional_data":false,"paper_date":"2022-11-10","paper":"/paper/internimage-exploring-large-scale-vision","paper_url":"https://arxiv.org/abs/2211.05778v4","paper_title":"InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions","code":"https://github.com/opengvlab/internimage","n_code_links":3,"official":{"repos":["opengvlab/internimage"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["listed"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":0,"sample_list":"/paper/internimage-exploring-large-scale-vision#ran","syntology_url":"https://syntology.ai/paper/2211.05778","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.05778"}}}},{"rank_in_archive_order":232,"model":"FastViT-MA36","metrics":{"Mean IoU (class)":"44.6"},"uses_additional_data":false,"paper_date":"2023-03-24","paper":"/paper/fastvit-a-fast-hybrid-vision-transformer","paper_url":"https://arxiv.org/abs/2303.14189v2","paper_title":"FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":6,"official":{"repos":["apple/ml-fastvit","rwightman/pytorch-image-models"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":4,"n_samples":5,"n_pointer_only_licence":5,"sample_list":"/paper/fastvit-a-fast-hybrid-vision-transformer#ran","syntology_url":"https://syntology.ai/paper/2303.14189","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.14189"}}}},{"rank_in_archive_order":233,"model":"FastViT-SA36","metrics":{"Mean IoU (class)":"42.9"},"uses_additional_data":false,"paper_date":"2023-03-24","paper":"/paper/fastvit-a-fast-hybrid-vision-transformer","paper_url":"https://arxiv.org/abs/2303.14189v2","paper_title":"FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":6,"official":{"repos":["apple/ml-fastvit","rwightman/pytorch-image-models"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":4,"n_samples":5,"n_pointer_only_licence":5,"sample_list":"/paper/fastvit-a-fast-hybrid-vision-transformer#ran","syntology_url":"https://syntology.ai/paper/2303.14189","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.14189"}}}},{"rank_in_archive_order":234,"model":"FastViT-SA24","metrics":{"Mean IoU (class)":"41"},"uses_additional_data":false,"paper_date":"2023-03-24","paper":"/paper/fastvit-a-fast-hybrid-vision-transformer","paper_url":"https://arxiv.org/abs/2303.14189v2","paper_title":"FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":6,"official":{"repos":["apple/ml-fastvit","rwightman/pytorch-image-models"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":4,"n_samples":5,"n_pointer_only_licence":5,"sample_list":"/paper/fastvit-a-fast-hybrid-vision-transformer#ran","syntology_url":"https://syntology.ai/paper/2303.14189","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.14189"}}}},{"rank_in_archive_order":235,"model":"FastViT-SA12","metrics":{"Mean IoU (class)":"38"},"uses_additional_data":false,"paper_date":"2023-03-24","paper":"/paper/fastvit-a-fast-hybrid-vision-transformer","paper_url":"https://arxiv.org/abs/2303.14189v2","paper_title":"FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":6,"official":{"repos":["apple/ml-fastvit","rwightman/pytorch-image-models"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":4,"n_samples":5,"n_pointer_only_licence":5,"sample_list":"/paper/fastvit-a-fast-hybrid-vision-transformer#ran","syntology_url":"https://syntology.ai/paper/2303.14189","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.14189"}}}}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"adjudicator":"Claude Opus 5.5","adjudicator_from":"groundwork/59_code_with_papers/LB_EXTRACTOR_PREREG.md (not recorded in lb_measurement.json; the file's frozen_commit, measured_on and counts equal the run the pre-registration records)","adjudicator_sensitivity":[69,70],"adjudicator_specificity":[101,103],"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication by a model (adjudicator) of accepted entries on a held-out split of archive papers, rules frozen before the test; adjudicator_sensitivity and adjudicator_specificity are its own controls as [judged right, of]; it was not measured on the newer papers placed here","measurement_sentence":"Measured before publishing, on held-out archive papers: the extractor was given 883 of them and produced output for 881 (the other 2 had no title and were excluded before any model call, so they are not part of this measurement). A model adjudicator (Claude Opus 5.5), blind to which entries were real, judged 108 of 110 accepted entries correct on those held-out archive papers; its own controls: 69 of 70 archive-confirmed entries judged true, 101 of 103 corrupted copies judged false. It was not measured on the newer papers whose results are placed on this site.","coverage":{"sentence":"Syntology has checked 8,886 of the 18,637 papers on this site that are newer than the archive (for 3,717 of them no archive leaderboard matched the paper's tables, so there was nothing further to check); 733 were read and have nothing to place (arXiv has no HTML version of the paper, or that version has no tables), 41 could not be read (the extractor's reply could not be parsed), and results from the other 8,977 appear after they are checked.","complete":false,"papers_newer_than_archive":18637,"papers_checked":8886,"papers_checked_no_leaderboard_matched":3717,"papers_read_nothing_to_place":733,"papers_could_not_be_read":41,"papers_could_not_be_read_by_status":{"unparseable":41},"papers_extracted_not_yet_verified":0,"boards_without_verdict":3,"papers_not_yet_extracted":8975},"board_status":{"sentence":"Of the 8,888 newer papers whose tables Syntology has read (8,886 checked in full and 2 with a leaderboard still awaiting a verdict), 11 had this board among the leaderboards the extractor considered for their tables (it keeps at most 10 boards per paper and 4 per dataset; the lists of 1,586 of the 8,888 were already full without this board, so if it was crowded out of them it is not counted), and 7 proposed a result; of those 7, 6 gave no cell that passed the extractor's own checks, 1 was rejected by the independent check, 0 await a verdict and 0 were placed.","note":"papers, from the extractor's own records, over the newer papers whose tables were read; proposed = no_cell_passed_checks + rejected_by_independent_check + accepted_not_placed + awaiting_verdict + placed; counts, never a rate","eligible":true,"eligible_note":"false when the extractor never considers this board: it loads only boards with archive rows and at least one metric column (lb_extract.py Boards), so no newer paper can be proposed here; archive_rows and metric_columns say which","archive_rows":235,"metric_columns":6,"papers_read":8888,"papers_read_checked":8886,"papers_read_awaiting_verdict":2,"papers_read_verified":8888,"papers_read_not_yet_verified":0,"papers_read_at_candidate_cap":1596,"papers_read_list_full_without_this_board":1586,"candidates":11,"candidates_capped_note":"candidates = papers that had this board among the leaderboards the extractor considered for their tables; the extractor keeps at most 10 per paper and 4 per dataset, so a board crowded out of a paper's list is not counted and candidates is a floor; papers_read_list_full_without_this_board counts the read papers whose list did not hold this board and had reached 10, or held 4 boards of this board's dataset (the only papers that could have crowded it out); papers_read_at_candidate_cap counts, over every board, the papers whose list reached 10","proposed":7,"no_cell_passed_checks":6,"rejected_by_independent_check":1,"accepted_not_placed":0,"awaiting_verdict":0,"placed":0,"placed_entries_listed":0,"file_lines_unreadable_as_read":0,"since_line":"Since the archive (Syntology): none placed; 7 newer papers judged to report on this board so far"},"judged_to_report":{"heading":"Newer papers whose tables Claude Sonnet 4.5 judged to report on this benchmark (a model's judgement, not a result; newest first by arXiv id)","judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"a_record_without_a_model":false,"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here","order":"newest first by arXiv id (the identifier's order, not a rank)","outcomes":{"placed":"placed","no_cell_passed_checks":"no cell passed the extractor's checks","refused_by_rule":"refused by a rule","rejected":"rejected by the independent check","accepted_not_placed":"accepted by the independent check but not placed by this site","awaiting":"awaiting a verdict"},"reason_note":"for refused_by_rule, the rules' plain words for the reason codes the record gives (never the quoted or the actual cell text); null for every other outcome","total":7,"shown_on_page":7,"no_cell_split":{"no_cell_passed_checks_in_ledger":6,"rows_refused_by_rule":6,"rows_no_cell_passed_checks":0},"rows":[{"arxiv_id":"2609.26297","outcome":"refused_by_rule","reason":"the row is an ablation variant, not the method itself"},{"arxiv_id":"2607.03784","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2607.02097","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric; the column header qualifies the metric in a way the leaderboard does not"},{"arxiv_id":"2604.14724","outcome":"rejected","reason":null},{"arxiv_id":"2601.17950","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric; the value is not on the scale of the leaderboard column's archive values; the row label the model quoted is not the row's label"},{"arxiv_id":"2511.21477","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2510.12764","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"}]},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per row: of M harvested code samples from that row's paper, n_ran executed on a synthesized fixture (n_ran = n_ran_checked + n_instrument; n_instrument counts failures of Syntology's instrument, not of the code); the other M - n_ran are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"rows_with_graph_line":156,"rows_with_any_sample_ran":150,"rows_with_a_run_with_no_instrument_failure":129,"official":{"state_rule":"the archive's official repositories have samples for this paper that ran: 'official (archive's flag): N ran' (N counts them, instrument failures included); they have samples, none ran: 'official: harvested, nothing ran'; they have no sample for this paper and another sample ran: 'community repositories only' when every sample that ran came from a repository the archive lists for the paper but neither marks official nor records as mentioned in it, or one Syntology harvested outside the archive's links, else 'official: no sample here; runs from other or unrecorded repositories' (a repository named in the paper or found in its text by Syntology, or no repository recorded); otherwise 'official: harvested for another paper' or 'official: not harvested'. Absent when the archive marks no repository official. Official is the archive's is_official flag, not an authorship verdict","flag":"the archive's is_official flag for the paper's code link; not a verdict on who wrote the code","rows_with_an_archive_official_repository":151,"rows_whose_official_repository_has_a_sample_that_ran":90,"rows_whose_official_repository_has_a_run_with_no_instrument_failure":70,"rows_community_repositories_only":40,"rows_runs_from_other_or_unrecorded_repositories":5,"note":"rows[].official, per row with a graph line: repos (marked official in the archive), state, n_ran and n_unverified (samples from those repositories), and ran_from_kinds (the kinds of repository the paper's samples that ran came from; 'unlocated' is no repository recorded)"},"filters":{"ran_modes":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"the page's filters hide rows and never renumber them; they read the Ran cell's counts, the same figures rows[].syntology and rows[].official carry"},"row_route":"rows[].syntology carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers","distinct_papers_with_graph_line":67,"distinct_papers_with_any_sample_ran":65,"distinct_papers_with_a_run_with_no_instrument_failure":56,"samples_over_distinct_papers":{"n_ran":830,"n_constructed":238,"n_ran_checked":579,"n_instrument":251,"n_unverified":408,"n_samples":1238,"n_pointer_only_licence":372,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":2045,"n_constructed":693,"n_ran_checked":1507,"n_instrument":538,"n_unverified":919,"n_samples":2964,"n_pointer_only_licence":894,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}},"record_sha256":"c2e1a0aece4431ee1973065b2437d8a1c874d952095fa1b9cf30934183b0d090","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}