{"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-val","task":{"name":"Semantic Segmentation","url":"/task/semantic-segmentation","note":null},"dataset":{"name":"ADE20K val","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":["mIoU","Pixel Accuracy"],"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":{"mIoU":null,"Pixel Accuracy":"higher"}},"counts":{"rows":95,"rows_with_code":86,"rows_with_paper_page":94,"rows_dated":94,"rows_using_additional_data":6},"rows":[{"rank_in_archive_order":1,"model":"BEiT-3","metrics":{"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":2,"model":"ViT-CoMer","metrics":{"mIoU":"62.1"},"uses_additional_data":false,"paper_date":"2024-03-13","paper":"/paper/vit-comer-vision-transformer-with","paper_url":"https://openreview.net/forum?id=srPMwpkWbR&invitationId=thecvf.com/CVPR/2024/Conference/Submission1221/-/Camera_Ready_Revision&referrer=%5BAuthor%20Console%5D(%2Fgroup%3Fid%3Dthecvf.com%2FCVPR%2F2024%2FConference%2FAuthors%23author-tasks)","paper_title":"ViT-CoMer: Vision Transformer with Convolutional Multi-scale Feature Interaction for Dense Predictions","code":"https://github.com/Traffic-X/ViT-CoMer","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":3,"model":"EVA","metrics":{"mIoU":"61.5"},"uses_additional_data":false,"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":4,"model":"FD-SwinV2-G","metrics":{"mIoU":"61.4"},"uses_additional_data":true,"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":5,"model":"MaskDINO-SwinL","metrics":{"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":6,"model":"OneFormer (InternImage-H, emb_dim=256, multi-scale, 896x896)","metrics":{"mIoU":"60.8"},"uses_additional_data":false,"paper_date":"2022-11-10","paper":"/paper/oneformer-one-transformer-to-rule-universal","paper_url":"https://arxiv.org/abs/2211.06220v2","paper_title":"OneFormer: One Transformer to Rule Universal Image Segmentation","code":"https://github.com/huggingface/transformers","n_code_links":4,"official":{"repos":["SHI-Labs/OneFormer"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":1,"n_samples":5,"n_pointer_only_licence":0,"sample_list":"/paper/oneformer-one-transformer-to-rule-universal#ran","syntology_url":"https://syntology.ai/paper/2211.06220","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.06220"}}}},{"rank_in_archive_order":7,"model":"ViT-Adapter-L (Mask2Former, BEiT pretrain)","metrics":{"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":8,"model":"SERNet-Former_v2","metrics":{"mIoU":"59.35"},"uses_additional_data":true,"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":9,"model":"OneFormer (DiNAT-L, multi-scale, 896x896)","metrics":{"mIoU":"58.6"},"uses_additional_data":false,"paper_date":"2022-11-10","paper":"/paper/oneformer-one-transformer-to-rule-universal","paper_url":"https://arxiv.org/abs/2211.06220v2","paper_title":"OneFormer: One Transformer to Rule Universal Image Segmentation","code":"https://github.com/huggingface/transformers","n_code_links":4,"official":{"repos":["SHI-Labs/OneFormer"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":1,"n_samples":5,"n_pointer_only_licence":0,"sample_list":"/paper/oneformer-one-transformer-to-rule-universal#ran","syntology_url":"https://syntology.ai/paper/2211.06220","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.06220"}}}},{"rank_in_archive_order":10,"model":"ViT-Adapter-L (UperNet, BEiT pretrain)","metrics":{"mIoU":"58.4"},"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":11,"model":"OneFormer (DiNAT-L, multi-scale, 640x640)","metrics":{"mIoU":"58.4"},"uses_additional_data":false,"paper_date":"2022-11-10","paper":"/paper/oneformer-one-transformer-to-rule-universal","paper_url":"https://arxiv.org/abs/2211.06220v2","paper_title":"OneFormer: One Transformer to Rule Universal Image Segmentation","code":"https://github.com/huggingface/transformers","n_code_links":4,"official":{"repos":["SHI-Labs/OneFormer"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":1,"n_samples":5,"n_pointer_only_licence":0,"sample_list":"/paper/oneformer-one-transformer-to-rule-universal#ran","syntology_url":"https://syntology.ai/paper/2211.06220","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.06220"}}}},{"rank_in_archive_order":12,"model":"RSSeg-ViT-L(BEiT pretrain)","metrics":{"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":13,"model":"EoMT (DINOv2-L, single-scale, 512x512)","metrics":{"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":14,"model":"OneFormer (Swin-L, multi-scale, 896x896)","metrics":{"mIoU":"58.3"},"uses_additional_data":false,"paper_date":"2022-11-10","paper":"/paper/oneformer-one-transformer-to-rule-universal","paper_url":"https://arxiv.org/abs/2211.06220v2","paper_title":"OneFormer: One Transformer to Rule Universal Image Segmentation","code":"https://github.com/huggingface/transformers","n_code_links":4,"official":{"repos":["SHI-Labs/OneFormer"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":1,"n_samples":5,"n_pointer_only_licence":0,"sample_list":"/paper/oneformer-one-transformer-to-rule-universal#ran","syntology_url":"https://syntology.ai/paper/2211.06220","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.06220"}}}},{"rank_in_archive_order":15,"model":"SeMask (SeMask Swin-L FaPN-Mask2Former)","metrics":{"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":16,"model":"SeMask (SeMask Swin-L MSFaPN-Mask2Former)","metrics":{"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":17,"model":"DiNAT-L (Mask2Former)","metrics":{"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":18,"model":"Mask2Former (Swin-L-FaPN, multiscale)","metrics":{"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":19,"model":"OneFormer (Swin-L, multi-scale, 640x640)","metrics":{"mIoU":"57.7"},"uses_additional_data":false,"paper_date":"2022-11-10","paper":"/paper/oneformer-one-transformer-to-rule-universal","paper_url":"https://arxiv.org/abs/2211.06220v2","paper_title":"OneFormer: One Transformer to Rule Universal Image Segmentation","code":"https://github.com/huggingface/transformers","n_code_links":4,"official":{"repos":["SHI-Labs/OneFormer"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":1,"n_samples":5,"n_pointer_only_licence":0,"sample_list":"/paper/oneformer-one-transformer-to-rule-universal#ran","syntology_url":"https://syntology.ai/paper/2211.06220","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.06220"}}}},{"rank_in_archive_order":20,"model":"SeMask (SeMask Swin-L Mask2Former)","metrics":{"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":21,"model":"SenFormer (BEiT-L)","metrics":{"mIoU":"57.1"},"uses_additional_data":false,"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":22,"model":"BEiT-L (ViT+UperNet, ImageNet-22k pretrain)","metrics":{"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":23,"model":"SeMask (SeMask Swin-L MSFaPN-Mask2Former, single-scale)","metrics":{"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":24,"model":"FaPN (MaskFormer, Swin-L, ImageNet-22k pretrain)","metrics":{"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":25,"model":"Mask2Former (Swin-L-FaPN)","metrics":{"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":26,"model":"SeMask (SeMask Swin-L MaskFormer)","metrics":{"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":27,"model":"CSWin-L (UperNet, ImageNet-22k pretrain)","metrics":{"mIoU":"55.7"},"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":28,"model":"MaskFormer (Swin-L, ImageNet-22k pretrain)","metrics":{"mIoU":"55.6"},"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":29,"model":"DeiT-L","metrics":{"mIoU":"55.6"},"uses_additional_data":false,"paper_date":"2022-04-14","paper":"/paper/deit-iii-revenge-of-the-vit","paper_url":"https://arxiv.org/abs/2204.07118v1","paper_title":"DeiT III: Revenge of the ViT","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":12,"official":null,"syntology":null},{"rank_in_archive_order":30,"model":"Focal-L (UperNet, ImageNet-22k pretrain)","metrics":{"mIoU":"55.4"},"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":31,"model":"SegViT ViT-Large","metrics":{"mIoU":"55.2"},"uses_additional_data":false,"paper_date":"2022-10-12","paper":"/paper/segvit-semantic-segmentation-with-plain","paper_url":"https://arxiv.org/abs/2210.05844v2","paper_title":"SegViT: Semantic Segmentation with Plain Vision Transformers","code":"https://github.com/zbwxp/SegVit","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":32,"model":"PatchDiverse + Swin-L (multi-scale test, upernet, ImageNet22k pretrain)","metrics":{"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":33,"model":"K-Net","metrics":{"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":34,"model":"DEPICT-SA (ViT-L 640x640 multi-scale)","metrics":{"mIoU":"54.3"},"uses_additional_data":false,"paper_date":"2024-11-05","paper":"/paper/rethinking-decoders-for-transformer-based","paper_url":"https://arxiv.org/abs/2411.03033v3","paper_title":"Rethinking Decoders for Transformer-based Semantic Segmentation: A Compression Perspective","code":"https://github.com/qishuaiwen/depict","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":35,"model":"SenFormer (Swin-L)","metrics":{"mIoU":"54.2"},"uses_additional_data":false,"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":36,"model":"DeiT-B","metrics":{"mIoU":"54.1"},"uses_additional_data":false,"paper_date":"2022-04-14","paper":"/paper/deit-iii-revenge-of-the-vit","paper_url":"https://arxiv.org/abs/2204.07118v1","paper_title":"DeiT III: Revenge of the ViT","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":12,"official":null,"syntology":null},{"rank_in_archive_order":37,"model":"MixMIM-L","metrics":{"mIoU":"53.8"},"uses_additional_data":false,"paper_date":"2022-05-26","paper":"/paper/mixmim-mixed-and-masked-image-modeling-for","paper_url":"https://arxiv.org/abs/2205.13137v4","paper_title":"MixMAE: Mixed and Masked Autoencoder for Efficient Pretraining of Hierarchical Vision Transformers","code":"https://github.com/sense-x/mixmim","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":38,"model":"Seg-L-Mask/16 (MS, ViT-L)","metrics":{"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":39,"model":"Swin-L (UperNet, ImageNet-22k pretrain)","metrics":{"mIoU":"53.5"},"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":40,"model":"SeMask (SeMask Swin-L FPN)","metrics":{"mIoU":"53.5"},"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":41,"model":"PatchConvNet-L120 (UperNet)","metrics":{"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":42,"model":"DEPICT-SA (ViT-L 640x640 single-scale)","metrics":{"mIoU":"52.9"},"uses_additional_data":false,"paper_date":"2024-11-05","paper":"/paper/rethinking-decoders-for-transformer-based","paper_url":"https://arxiv.org/abs/2411.03033v3","paper_title":"Rethinking Decoders for Transformer-based Semantic Segmentation: A Compression Perspective","code":"https://github.com/qishuaiwen/depict","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":43,"model":"PatchConvNet-B120 (UperNet)","metrics":{"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":44,"model":"SegFormer-B5(MS, 87M #Params, ImageNet-1K pretrain)","metrics":{"mIoU":"51.8"},"uses_additional_data":false,"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":45,"model":"Light-Ham (VAN-Huge, 61M, IN-1k, MS)","metrics":{"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":46,"model":"CrossFormer (ImageNet1k-pretrain, UPerNet, multi-scale test)","metrics":{"Pixel Accuracy":"84.0%","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":47,"model":"PatchConvNet-B60 (UperNet)","metrics":{"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":48,"model":"Light-Ham (VAN-Large, 46M, IN-1k, MS)","metrics":{"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":49,"model":"UperNet Shuffle-B","metrics":{"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":50,"model":"ELSA-Swin-S","metrics":{"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":51,"model":"MixMIM-B","metrics":{"mIoU":"50.3"},"uses_additional_data":false,"paper_date":"2022-05-26","paper":"/paper/mixmim-mixed-and-masked-image-modeling-for","paper_url":"https://arxiv.org/abs/2205.13137v4","paper_title":"MixMAE: Mixed and Masked Autoencoder for Efficient Pretraining of Hierarchical Vision Transformers","code":"https://github.com/sense-x/mixmim","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":52,"model":"Twins-SVT-L (UperNet, ImageNet-1k pretrain)","metrics":{"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":53,"model":"Seg-B-Mask/16 (MS, ViT-B)","metrics":{"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":54,"model":"Swin-B (UperNet, ImageNet-1k pretrain)","metrics":{"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":55,"model":"gSwin-S","metrics":{"Pixel Accuracy":"83.43","mIoU":"49.69"},"uses_additional_data":false,"paper_date":"2022-08-24","paper":"/paper/gswin-gated-mlp-vision-model-with","paper_url":"https://arxiv.org/abs/2208.11718v1","paper_title":"gSwin: Gated MLP Vision Model with Hierarchical Structure of Shifted Window","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":56,"model":"Seg-B/8 (MS, ViT-B)","metrics":{"Pixel Accuracy":"83.37","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":57,"model":"UperNet Shuffle-S","metrics":{"mIoU":"49.6"},"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":58,"model":"Light-Ham (VAN-Base, 27M, IN-1k, MS)","metrics":{"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":59,"model":"PatchConvNet-S60 (UperNet)","metrics":{"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":60,"model":"DPT-Hybrid","metrics":{"Pixel Accuracy":"83.11","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":61,"model":"DaViT-S (UperNet)","metrics":{"mIoU":"48.8"},"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":62,"model":"ResNeSt-200","metrics":{"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":63,"model":"HRNetV2 + OCR + RMI (PaddleClas pretrained)","metrics":{"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":64,"model":"gSwin-T","metrics":{"Pixel Accuracy":"82.60","mIoU":"47.63"},"uses_additional_data":false,"paper_date":"2022-08-24","paper":"/paper/gswin-gated-mlp-vision-model-with","paper_url":"https://arxiv.org/abs/2208.11718v1","paper_title":"gSwin: Gated MLP Vision Model with Hierarchical Structure of Shifted Window","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":65,"model":"ResNeSt-269","metrics":{"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":66,"model":"UperNet Shuffle-T","metrics":{"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":67,"model":"DCNAS","metrics":{"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":68,"model":"ResNeSt-101","metrics":{"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":69,"model":"Seg-S-Mask/16 (MS, ViT-S)","metrics":{"mIoU":"46.9"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":70,"model":"Swin-S (RPE w/ GAB)","metrics":{"mIoU":"46.41"},"uses_additional_data":false,"paper_date":"2023-05-08","paper":"/paper/understanding-gaussian-attention-bias-of","paper_url":"https://arxiv.org/abs/2305.04722v1","paper_title":"Understanding Gaussian Attention Bias of Vision Transformers Using Effective Receptive Fields","code":"https://github.com/kmbmjn/GaussianAttentionBias","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":71,"model":"DaViT-B (UperNet)","metrics":{"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":72,"model":"CPN(ResNet-101)","metrics":{"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":73,"model":"MultiMAE (ViT-B)","metrics":{"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":74,"model":"PyConvSegNet-152","metrics":{"Pixel Accuracy":"82.49","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":75,"model":"DNL","metrics":{"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":76,"model":"CTNet","metrics":{"mIoU":"45.94"},"uses_additional_data":false,"paper_date":"2021-04-20","paper":"/paper/ctnet-context-based-tandem-network-for","paper_url":"https://arxiv.org/abs/2104.09805v1","paper_title":"CTNet: Context-based Tandem Network for Semantic Segmentation","code":"https://github.com/syp2ysy/CTNet","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":77,"model":"ACNet (ResNet-101)","metrics":{"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":78,"model":"ACNet(ResNet-101)","metrics":{"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":79,"model":"OCR (HRNetV2-W48)","metrics":{"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":80,"model":"EANet (ResNet-101)","metrics":{"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":81,"model":"OCR (ResNet-101)","metrics":{"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":82,"model":"Asymmetric ALNN","metrics":{"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":83,"model":"gSwin-VT","metrics":{"Pixel Accuracy":"81.79","mIoU":"45.07"},"uses_additional_data":false,"paper_date":"2022-08-24","paper":"/paper/gswin-gated-mlp-vision-model-with","paper_url":"https://arxiv.org/abs/2208.11718v1","paper_title":"gSwin: Gated MLP Vision Model with Hierarchical Structure of Shifted Window","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":84,"model":"LaU-regression-loss","metrics":{"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":85,"model":"EncNet (ResNet-101)","metrics":{"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":86,"model":"SGR (ResNet-101)","metrics":{"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":87,"model":"Auto-DeepLab-L","metrics":{"Pixel Accuracy":"81.72","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":88,"model":"PSANet (ResNet-101)","metrics":{"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":89,"model":"DSSPN (ResNet-101)","metrics":{"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":90,"model":"PSPNet (ResNet-152)","metrics":{"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":91,"model":"PSPNet (ResNet-101)","metrics":{"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":92,"model":"HRNetV2 (HRNetV2-W48)","metrics":{"mIoU":"42.99"},"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":93,"model":"UperNet (ResNet-101)","metrics":{"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":94,"model":"RefineNet (ResNet-152)","metrics":{"mIoU":"40.70"},"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":95,"model":"RefineNet (ResNet-101)","metrics":{"mIoU":"40.20"},"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"}}}}],"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), 25 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 1,571 of the 8,888 were already full without this board, so if it was crowded out of them it is not counted), and 17 proposed a result; of those 17, 16 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":95,"metric_columns":2,"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":1571,"candidates":25,"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":17,"no_cell_passed_checks":16,"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; 17 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":17,"shown_on_page":17,"no_cell_split":{"no_cell_passed_checks_in_ledger":16,"rows_refused_by_rule":16,"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 reports a different split or setting than the leaderboard"},{"arxiv_id":"2607.02097","outcome":"refused_by_rule","reason":"the column header qualifies the metric in a way the leaderboard does not"},{"arxiv_id":"2606.04373","outcome":"refused_by_rule","reason":"the table reports a different split or setting than the leaderboard"},{"arxiv_id":"2605.24025","outcome":"refused_by_rule","reason":"the model gave no value to check against the cell"},{"arxiv_id":"2605.19289","outcome":"refused_by_rule","reason":"the column header qualifies the metric in a way the leaderboard does not"},{"arxiv_id":"2604.14724","outcome":"refused_by_rule","reason":"the column header qualifies the metric in a way the leaderboard does not"},{"arxiv_id":"2602.14134","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2602.06862","outcome":"refused_by_rule","reason":"the table reports a different split or setting than the leaderboard"},{"arxiv_id":"2602.03227","outcome":"refused_by_rule","reason":"the table reports a different split or setting than the leaderboard; the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2602.01219","outcome":"refused_by_rule","reason":"the table reports a different split or setting than the leaderboard"},{"arxiv_id":"2601.17950","outcome":"refused_by_rule","reason":"the table reports a different split or setting than the leaderboard; the table's column header does not name the leaderboard's metric; the row label the model quoted is not the row's label"},{"arxiv_id":"2601.08602","outcome":"refused_by_rule","reason":"the table reports a different split or setting than the leaderboard"},{"arxiv_id":"2601.01167","outcome":"rejected","reason":null},{"arxiv_id":"2511.21477","outcome":"refused_by_rule","reason":"the table reports a different split or setting than the leaderboard"},{"arxiv_id":"2511.12594","outcome":"refused_by_rule","reason":"the table does not name the leaderboard's dataset"},{"arxiv_id":"2510.12764","outcome":"refused_by_rule","reason":"the table reports a different split or setting than the leaderboard; 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":54,"rows_with_any_sample_ran":54,"rows_with_a_run_with_no_instrument_failure":49,"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":50,"rows_whose_official_repository_has_a_sample_that_ran":28,"rows_whose_official_repository_has_a_run_with_no_instrument_failure":16,"rows_community_repositories_only":18,"rows_runs_from_other_or_unrecorded_repositories":1,"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":32,"distinct_papers_with_any_sample_ran":32,"distinct_papers_with_a_run_with_no_instrument_failure":27,"samples_over_distinct_papers":{"n_ran":440,"n_constructed":93,"n_ran_checked":274,"n_instrument":166,"n_unverified":233,"n_samples":673,"n_pointer_only_licence":173,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":727,"n_constructed":143,"n_ran_checked":461,"n_instrument":266,"n_unverified":396,"n_samples":1123,"n_pointer_only_licence":290,"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":"be9d0c8c20b772cc0ef59f9037e3b31c98ea82807bfffc7f73c095dc97300cca","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}