{"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-cityscapes-val","task":{"name":"Semantic Segmentation","url":"/task/semantic-segmentation","note":null},"dataset":{"name":"Cityscapes val","url":"/dataset/cityscapes"},"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","FPS","Validation mIoU"],"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,"FPS":null,"Validation mIoU":null}},"counts":{"rows":99,"rows_with_code":93,"rows_with_paper_page":98,"rows_dated":98,"rows_using_additional_data":15},"rows":[{"rank_in_archive_order":1,"model":"ViT-P (InternImage-H)","metrics":{"mIoU":"87.4"},"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":"SERNet-Former","metrics":{"Validation mIoU":"87.35","mIoU":"87.35"},"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":3,"model":"MetaPrompt-SD","metrics":{"mIoU":"87.1"},"uses_additional_data":true,"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":4,"model":"InternImage-H","metrics":{"mIoU":"87"},"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":5,"model":"HRNetV2-OCR+PSA","metrics":{"mIoU":"86.93"},"uses_additional_data":true,"paper_date":"2021-07-02","paper":"/paper/polarized-self-attention-towards-high-quality-1","paper_url":"https://arxiv.org/abs/2107.00782v2","paper_title":"Polarized Self-Attention: Towards High-quality Pixel-wise Regression","code":"https://github.com/PaddlePaddle/PaddleSeg","n_code_links":6,"official":null,"syntology":null},{"rank_in_archive_order":6,"model":"InternImage-XL","metrics":{"mIoU":"86.4"},"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":7,"model":"HRNet-OCR","metrics":{"mIoU":"86.3"},"uses_additional_data":true,"paper_date":"2020-05-21","paper":"/paper/hierarchical-multi-scale-attention-for","paper_url":"https://arxiv.org/abs/2005.10821v1","paper_title":"Hierarchical Multi-Scale Attention for Semantic Segmentation","code":"https://github.com/PaddlePaddle/PaddleSeg","n_code_links":8,"official":{"repos":["NVIDIA/semantic-segmentation"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":1,"n_samples":9,"n_pointer_only_licence":4,"sample_list":"/paper/hierarchical-multi-scale-attention-for#ran","syntology_url":"https://syntology.ai/paper/2005.10821","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.10821"}}}},{"rank_in_archive_order":8,"model":"Depth Anything","metrics":{"mIoU":"86.2"},"uses_additional_data":false,"paper_date":"2024-01-19","paper":"/paper/depth-anything-unleashing-the-power-of-large","paper_url":"https://arxiv.org/abs/2401.10891v2","paper_title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","code":"https://github.com/LiheYoung/Depth-Anything","n_code_links":7,"official":{"repos":["LiheYoung/Depth-Anything"],"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":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":2,"n_samples":11,"n_pointer_only_licence":0,"sample_list":"/paper/depth-anything-unleashing-the-power-of-large#ran","syntology_url":"https://syntology.ai/paper/2401.10891","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.10891"}}}},{"rank_in_archive_order":9,"model":"OneFormer (ConvNeXt-XL, Mapillary, multi-scale)","metrics":{"mIoU":"85.8"},"uses_additional_data":true,"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","metrics":{"mIoU":"85.8"},"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":"SeMask (SeMask Swin-L Mask2Former)","metrics":{"mIoU":"84.98"},"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":12,"model":"Sequential Ensemble (MiT-B5 + HRNet)","metrics":{"mIoU":"84.8"},"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":13,"model":"Soft Labells (HRnet)","metrics":{"mIoU":"84.8"},"uses_additional_data":false,"paper_date":"2023-02-27","paper":"/paper/soft-labelling-for-semantic-segmentation","paper_url":"https://arxiv.org/abs/2302.13961v3","paper_title":"Soft labelling for semantic segmentation: Bringing coherence to label down-sampling","code":"https://github.com/vpulab/soft-labels-ss","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":14,"model":"OneFormer (ConvNeXt-XL, multi-scale)","metrics":{"mIoU":"84.6"},"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":15,"model":"DiNAT-L (Mask2Former)","metrics":{"mIoU":"84.5"},"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":16,"model":"OneFormer (Swin-L, multi-scale)","metrics":{"mIoU":"84.4"},"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":17,"model":"VPNeXt","metrics":{"mIoU":"84.4"},"uses_additional_data":false,"paper_date":"2025-02-23","paper":"/paper/vpnext-rethinking-dense-decoding-for-plain","paper_url":"https://arxiv.org/abs/2502.16654v1","paper_title":"VPNeXt -- Rethinking Dense Decoding for Plain Vision Transformer","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":18,"model":"VOLO-D4 (MS, ImageNet1k pretrain)","metrics":{"mIoU":"84.3"},"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":19,"model":"Mask2Former (Swin-L)","metrics":{"mIoU":"84.3"},"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":20,"model":"EoMT (DINOv2-L, single-scale, 1024x1024)","metrics":{"FPS":"25","Validation mIoU":"84.2","mIoU":"84.2"},"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":21,"model":"SegFormer (MiT-B5, Mapillary)","metrics":{"mIoU":"84.0"},"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":22,"model":"DDP (ConvNeXt-L, step-3)","metrics":{"mIoU":"83.9"},"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":23,"model":"HRNetV2 + OCR + RMI (PaddleClas pretrained)","metrics":{"mIoU":"83.6"},"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":24,"model":"PatchDiverse + Swin-L (multi-scale test, upernet, ImageNet22k pretrain)","metrics":{"mIoU":"83.6%"},"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":25,"model":"SynBoost","metrics":{"mIoU":"83.5"},"uses_additional_data":false,"paper_date":"2021-03-09","paper":"/paper/pixel-wise-anomaly-detection-in-complex","paper_url":"https://arxiv.org/abs/2103.05445v1","paper_title":"Pixel-wise Anomaly Detection in Complex Driving Scenes","code":"https://github.com/giandbt/synboost","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":26,"model":"HRNetV2+OCR+CBL(ImageNet pretrained)","metrics":{"mIoU":"83.4"},"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":27,"model":"EfficientViT-B3 (r1184x2368)","metrics":{"mIoU":"83.2"},"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":28,"model":"HRViT-b3 (SegFormer, SS)","metrics":{"mIoU":"83.16%"},"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":29,"model":"SpineNet-S143+ (single-scale test)","metrics":{"mIoU":"83.04%"},"uses_additional_data":false,"paper_date":"2021-03-23","paper":"/paper/dilated-spinenet-for-semantic-segmentation","paper_url":"https://arxiv.org/abs/2103.12270v1","paper_title":"Dilated SpineNet for Semantic Segmentation","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":30,"model":"HRViT-b2 (SegFormer, SS)","metrics":{"mIoU":"82.81%"},"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":31,"model":"FAN-L-Hybrid+STL","metrics":{"mIoU":"82.8"},"uses_additional_data":false,"paper_date":"2024-01-08","paper":"/paper/fully-attentional-networks-with-self-emerging-1","paper_url":"https://arxiv.org/abs/2401.03844v1","paper_title":"Fully Attentional Networks with Self-emerging Token Labeling","code":"https://github.com/NVlabs/STL","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":32,"model":"ResNeSt-200","metrics":{"mIoU":"82.7"},"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":33,"model":"WaveMix","metrics":{"mIoU":"82.7"},"uses_additional_data":false,"paper_date":"2022-05-28","paper":"/paper/wavemix-lite-a-resource-efficient-neural","paper_url":"https://arxiv.org/abs/2205.14375v5","paper_title":"WaveMix: A Resource-efficient Neural Network for Image Analysis","code":"https://github.com/pranavphoenix/WaveMix","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":34,"model":"CMX (B4)","metrics":{"mIoU":"82.6"},"uses_additional_data":false,"paper_date":"2022-03-09","paper":"/paper/cmx-cross-modal-fusion-for-rgb-x-semantic","paper_url":"https://arxiv.org/abs/2203.04838v5","paper_title":"CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers","code":"https://github.com/huaaaliu/rgbx_semantic_segmentation","n_code_links":1,"official":{"repos":["huaaaliu/rgbx_semantic_segmentation"],"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/cmx-cross-modal-fusion-for-rgb-x-semantic#ran","syntology_url":"https://syntology.ai/paper/2203.04838","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.04838"}}}},{"rank_in_archive_order":35,"model":"WaveMix-256/16 (Level-4)","metrics":{"mIoU":"82.60"},"uses_additional_data":false,"paper_date":"2022-05-28","paper":"/paper/wavemix-lite-a-resource-efficient-neural","paper_url":"https://arxiv.org/abs/2205.14375v5","paper_title":"WaveMix: A Resource-efficient Neural Network for Image Analysis","code":"https://github.com/pranavphoenix/WaveMix","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":36,"model":"FAN-L-Hybrid","metrics":{"mIoU":"82.3"},"uses_additional_data":false,"paper_date":"2022-04-26","paper":"/paper/understanding-the-robustness-in-vision","paper_url":"https://arxiv.org/abs/2204.12451v4","paper_title":"Understanding The Robustness in Vision Transformers","code":"https://github.com/nvlabs/fan","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":37,"model":"SETR-PUP (80k, MS)","metrics":{"mIoU":"82.15"},"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":38,"model":"DSNet-Base(single-scale)","metrics":{"mIoU":"82.0"},"uses_additional_data":false,"paper_date":"2024-06-06","paper":"/paper/dsnet-a-novel-way-to-use-atrous-convolutions","paper_url":"https://arxiv.org/abs/2406.03702v1","paper_title":"DSNet: A Novel Way to Use Atrous Convolutions in Semantic Segmentation","code":"https://github.com/takaniwa/dsnet","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":39,"model":"EANet","metrics":{"mIoU":"81.7%"},"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":40,"model":"HRViT-b1 (SegFormer, SS)","metrics":{"mIoU":"81.63%"},"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":41,"model":"CMX (B2)","metrics":{"mIoU":"81.6"},"uses_additional_data":false,"paper_date":"2022-03-09","paper":"/paper/cmx-cross-modal-fusion-for-rgb-x-semantic","paper_url":"https://arxiv.org/abs/2203.04838v5","paper_title":"CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers","code":"https://github.com/huaaaliu/rgbx_semantic_segmentation","n_code_links":1,"official":{"repos":["huaaaliu/rgbx_semantic_segmentation"],"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/cmx-cross-modal-fusion-for-rgb-x-semantic#ran","syntology_url":"https://syntology.ai/paper/2203.04838","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.04838"}}}},{"rank_in_archive_order":42,"model":"Trans4Trans","metrics":{"mIoU":"81.54%"},"uses_additional_data":false,"paper_date":"2021-08-20","paper":"/paper/trans4trans-efficient-transformer-for-1","paper_url":"https://arxiv.org/abs/2108.09174v1","paper_title":"Trans4Trans: Efficient Transformer for Transparent Object and Semantic Scene Segmentation in Real-World Navigation Assistance","code":"https://github.com/jamycheung/Trans4Trans","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":43,"model":"Panoptic-DeepLab","metrics":{"mIoU":"81.5%"},"uses_additional_data":false,"paper_date":"2019-11-22","paper":"/paper/panoptic-deeplab-a-simple-strong-and-fast","paper_url":"https://arxiv.org/abs/1911.10194v3","paper_title":"Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation","code":"https://github.com/tensorflow/models/tree/master/official/projects/panoptic","n_code_links":9,"official":{"repos":["bowenc0221/panoptic-deeplab"],"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":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":4,"n_samples":9,"n_pointer_only_licence":1,"sample_list":"/paper/panoptic-deeplab-a-simple-strong-and-fast#ran","syntology_url":"https://syntology.ai/paper/1911.10194","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.10194"}}}},{"rank_in_archive_order":44,"model":"Soft Labells (Deeplab)","metrics":{"mIoU":"81.5"},"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":45,"model":"HRNetV2 (HRNetV2-W48)","metrics":{"mIoU":"81.1"},"uses_additional_data":false,"paper_date":"2019-08-20","paper":"/paper/190807919","paper_url":"https://arxiv.org/abs/1908.07919v2","paper_title":"Deep High-Resolution Representation Learning for Visual Recognition","code":"https://github.com/open-mmlab/mmdetection","n_code_links":42,"official":null,"syntology":{"n_ran":21,"n_constructed":0,"n_ran_checked":16,"n_instrument":5,"n_unverified":13,"n_samples":34,"n_pointer_only_licence":21,"sample_list":"/paper/190807919#ran","syntology_url":"https://syntology.ai/paper/1908.07919","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.07919"}}}},{"rank_in_archive_order":46,"model":"Trans4PASS (Small)","metrics":{"mIoU":"81.1%"},"uses_additional_data":false,"paper_date":"2022-03-02","paper":"/paper/bending-reality-distortion-aware-transformers","paper_url":"https://arxiv.org/abs/2203.01452v2","paper_title":"Bending Reality: Distortion-aware Transformers for Adapting to Panoramic Semantic Segmentation","code":"https://github.com/jamycheung/trans4pass","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":47,"model":"DEPICT-SA (ViT-L multi-scale)","metrics":{"mIoU":"81.0"},"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":48,"model":"OCR (ResNet-101-FCN)","metrics":{"mIoU":"80.6"},"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":49,"model":"RepVGG-B2","metrics":{"mIoU":"80.57%"},"uses_additional_data":false,"paper_date":"2021-01-11","paper":"/paper/repvgg-making-vgg-style-convnets-great-again","paper_url":"https://arxiv.org/abs/2101.03697v3","paper_title":"RepVGG: Making VGG-style ConvNets Great Again","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":25,"official":{"repos":["DingXiaoH/RepVGG"],"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","unlocated"]},"syntology":{"n_ran":13,"n_constructed":7,"n_ran_checked":8,"n_instrument":5,"n_unverified":3,"n_samples":16,"n_pointer_only_licence":6,"sample_list":"/paper/repvgg-making-vgg-style-convnets-great-again#ran","syntology_url":"https://syntology.ai/paper/2101.03697","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.03697"}}}},{"rank_in_archive_order":50,"model":"DSNet(single-scale)","metrics":{"FPS":"81.9","mIoU":"80.4"},"uses_additional_data":false,"paper_date":"2024-06-06","paper":"/paper/dsnet-a-novel-way-to-use-atrous-convolutions","paper_url":"https://arxiv.org/abs/2406.03702v1","paper_title":"DSNet: A Novel Way to Use Atrous Convolutions in Semantic Segmentation","code":"https://github.com/takaniwa/dsnet","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":51,"model":"SeMask (SeMask Swin-L FPN)","metrics":{"mIoU":"80.39"},"uses_additional_data":true,"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":52,"model":"Auto-DeepLab-L","metrics":{"mIoU":"80.33%"},"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":53,"model":"SML","metrics":{"mIoU":"80.33"},"uses_additional_data":false,"paper_date":"2021-07-23","paper":"/paper/standardized-max-logits-a-simple-yet","paper_url":"https://arxiv.org/abs/2107.11264v4","paper_title":"Standardized Max Logits: A Simple yet Effective Approach for Identifying Unexpected Road Obstacles in Urban-Scene Segmentation","code":"https://github.com/shjung13/standardized-max-logits","n_code_links":1,"official":{"repos":["shjung13/standardized-max-logits"],"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/standardized-max-logits-a-simple-yet#ran","syntology_url":"https://syntology.ai/paper/2107.11264","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.11264"}}}},{"rank_in_archive_order":54,"model":"Multiscale DEQ (MDEQ-XL)","metrics":{"mIoU":"80.3%"},"uses_additional_data":false,"paper_date":"2020-06-15","paper":"/paper/multiscale-deep-equilibrium-models","paper_url":"https://arxiv.org/abs/2006.08656v2","paper_title":"Multiscale Deep Equilibrium Models","code":"https://github.com/locuslab/deq","n_code_links":4,"official":{"repos":["locuslab/mdeq"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":10,"n_constructed":6,"n_ran_checked":7,"n_instrument":3,"n_unverified":4,"n_samples":14,"n_pointer_only_licence":4,"sample_list":"/paper/multiscale-deep-equilibrium-models#ran","syntology_url":"https://syntology.ai/paper/2006.08656","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.08656"}}}},{"rank_in_archive_order":55,"model":"HRNetV2 (HRNetV2-W40)","metrics":{"mIoU":"80.2"},"uses_additional_data":false,"paper_date":"2019-08-20","paper":"/paper/190807919","paper_url":"https://arxiv.org/abs/1908.07919v2","paper_title":"Deep High-Resolution Representation Learning for Visual Recognition","code":"https://github.com/open-mmlab/mmdetection","n_code_links":42,"official":null,"syntology":{"n_ran":21,"n_constructed":0,"n_ran_checked":16,"n_instrument":5,"n_unverified":13,"n_samples":34,"n_pointer_only_licence":21,"sample_list":"/paper/190807919#ran","syntology_url":"https://syntology.ai/paper/1908.07919","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.07919"}}}},{"rank_in_archive_order":56,"model":"PSPNet (Dilated-ResNet-101)","metrics":{"mIoU":"79.7"},"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":57,"model":"DeepLabv3+ (Dilated-Xception-71)","metrics":{"mIoU":"79.6"},"uses_additional_data":false,"paper_date":"2018-02-07","paper":"/paper/encoder-decoder-with-atrous-separable","paper_url":"http://arxiv.org/abs/1802.02611v3","paper_title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","code":"https://github.com/tensorflow/models/tree/master/research/deeplab","n_code_links":78,"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":44,"n_constructed":17,"n_ran_checked":28,"n_instrument":16,"n_unverified":28,"n_samples":72,"n_pointer_only_licence":40,"sample_list":"/paper/encoder-decoder-with-atrous-separable#ran","syntology_url":"https://syntology.ai/paper/1802.02611","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.02611"}}}},{"rank_in_archive_order":58,"model":"Trans4PASS (Tiny)","metrics":{"mIoU":"79.1%"},"uses_additional_data":false,"paper_date":"2022-03-02","paper":"/paper/bending-reality-distortion-aware-transformers","paper_url":"https://arxiv.org/abs/2203.01452v2","paper_title":"Bending Reality: Distortion-aware Transformers for Adapting to Panoramic Semantic Segmentation","code":"https://github.com/jamycheung/trans4pass","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":59,"model":"DEPICT-SA (ViT-L single-scale)","metrics":{"mIoU":"78.8"},"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":60,"model":"SemanticFPN P2-P5 + PointRend","metrics":{"mIoU":"78.6"},"uses_additional_data":false,"paper_date":"2019-12-17","paper":"/paper/pointrend-image-segmentation-as-rendering","paper_url":"https://arxiv.org/abs/1912.08193v2","paper_title":"PointRend: Image Segmentation as Rendering","code":"https://github.com/facebookresearch/detectron2/tree/master/projects/PointRend","n_code_links":14,"official":{"repos":["facebookresearch/detectron2"],"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":16,"n_constructed":0,"n_ran_checked":11,"n_instrument":5,"n_unverified":2,"n_samples":18,"n_pointer_only_licence":0,"sample_list":"/paper/pointrend-image-segmentation-as-rendering#ran","syntology_url":"https://syntology.ai/paper/1912.08193","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.08193"}}}},{"rank_in_archive_order":61,"model":"DeepLabv3 (Dilated-ResNet-101)","metrics":{"mIoU":"78.5%"},"uses_additional_data":false,"paper_date":"2017-06-17","paper":"/paper/rethinking-atrous-convolution-for-semantic","paper_url":"http://arxiv.org/abs/1706.05587v3","paper_title":"Rethinking Atrous Convolution for Semantic Image Segmentation","code":"https://github.com/tensorflow/models","n_code_links":77,"official":null,"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":4,"n_samples":7,"n_pointer_only_licence":3,"sample_list":"/paper/rethinking-atrous-convolution-for-semantic#ran","syntology_url":"https://syntology.ai/paper/1706.05587","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1706.05587"}}}},{"rank_in_archive_order":62,"model":"StreamDEQ (8 iterations)","metrics":{"FPS":"1.1","mIoU":"78.2"},"uses_additional_data":false,"paper_date":"2022-04-28","paper":"/paper/streaming-multiscale-deep-equilibrium-models","paper_url":"https://arxiv.org/abs/2204.13492v4","paper_title":"Representation Recycling for Streaming Video Analysis","code":"https://github.com/ufukertenli/streamdeq-code","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":63,"model":"Multiscale DEQ (MDEQ-large)","metrics":{"mIoU":"77.8%"},"uses_additional_data":false,"paper_date":"2020-06-15","paper":"/paper/multiscale-deep-equilibrium-models","paper_url":"https://arxiv.org/abs/2006.08656v2","paper_title":"Multiscale Deep Equilibrium Models","code":"https://github.com/locuslab/deq","n_code_links":4,"official":{"repos":["locuslab/mdeq"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":10,"n_constructed":6,"n_ran_checked":7,"n_instrument":3,"n_unverified":4,"n_samples":14,"n_pointer_only_licence":4,"sample_list":"/paper/multiscale-deep-equilibrium-models#ran","syntology_url":"https://syntology.ai/paper/2006.08656","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.08656"}}}},{"rank_in_archive_order":64,"model":"HALO","metrics":{"mIoU":"77.8"},"uses_additional_data":false,"paper_date":"2023-06-19","paper":"/paper/hyperbolic-active-learning-for-semantic","paper_url":"https://arxiv.org/abs/2306.11180v5","paper_title":"Hyperbolic Active Learning for Semantic Segmentation under Domain Shift","code":"https://github.com/paolomandica/HALO","n_code_links":1,"official":{"repos":["paolomandica/HALO"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["official"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":5,"n_samples":8,"n_pointer_only_licence":0,"sample_list":"/paper/hyperbolic-active-learning-for-semantic#ran","syntology_url":"https://syntology.ai/paper/2306.11180","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.11180"}}}},{"rank_in_archive_order":65,"model":"DetCon_B","metrics":{"mIoU":"77.0%"},"uses_additional_data":true,"paper_date":"2021-03-19","paper":"/paper/efficient-visual-pretraining-with-contrastive","paper_url":"https://arxiv.org/abs/2103.10957v2","paper_title":"Efficient Visual Pretraining with Contrastive Detection","code":"https://github.com/deepmind/detcon","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":66,"model":"EEEA-Net-C2 (ours)","metrics":{"mIoU":"76.8"},"uses_additional_data":false,"paper_date":"2021-08-13","paper":"/paper/eeea-net-an-early-exit-evolutionary-neural","paper_url":"https://arxiv.org/abs/2108.06156v1","paper_title":"EEEA-Net: An Early Exit Evolutionary Neural Architecture Search","code":"https://github.com/chakkritte/eeea-net","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":67,"model":"WaveMixLite-256/16","metrics":{"mIoU":"76.79"},"uses_additional_data":false,"paper_date":"2022-10-13","paper":"/paper/wavemix-lite-a-resource-efficient-neural-1","paper_url":"https://openreview.net/forum?id=y_icnxeeUcl","paper_title":"WaveMix-Lite: A Resource-efficient Neural Network for Image Analysis","code":"https://github.com/pranavphoenix/WaveMix","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":68,"model":"SwinMTL","metrics":{"mIoU":"76.41"},"uses_additional_data":false,"paper_date":"2024-03-15","paper":"/paper/swinmtl-a-shared-architecture-for","paper_url":"https://arxiv.org/abs/2403.10662v1","paper_title":"SwinMTL: A Shared Architecture for Simultaneous Depth Estimation and Semantic Segmentation from Monocular Camera Images","code":"https://github.com/pardistaghavi/swinmtl","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":69,"model":"CSFNet-2","metrics":{"FPS":"72.3 (3090)","mIoU":"76.36"},"uses_additional_data":false,"paper_date":"2024-07-01","paper":"/paper/csfnet-a-cosine-similarity-fusion-network-for","paper_url":"https://arxiv.org/abs/2407.01328v1","paper_title":"CSFNet: A Cosine Similarity Fusion Network for Real-Time RGB-X Semantic Segmentation of Driving Scenes","code":"https://github.com/Danial-Qashqai/CSFNet","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":70,"model":"RepMLPNet-D256","metrics":{"mIoU":"76.27"},"uses_additional_data":false,"paper_date":"2021-12-21","paper":"/paper/repmlpnet-hierarchical-vision-mlp-with-re","paper_url":"https://arxiv.org/abs/2112.11081v2","paper_title":"RepMLPNet: Hierarchical Vision MLP with Re-parameterized Locality","code":"https://github.com/towhee-io/towhee","n_code_links":4,"official":{"repos":["DingXiaoH/RepMLP"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":3,"sample_list":"/paper/repmlpnet-hierarchical-vision-mlp-with-re#ran","syntology_url":"https://syntology.ai/paper/2112.11081","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.11081"}}}},{"rank_in_archive_order":71,"model":"Dilated-ResNet (Dilated-ResNet-101)","metrics":{"mIoU":"75.7"},"uses_additional_data":false,"paper_date":"2015-12-10","paper":"/paper/deep-residual-learning-for-image-recognition","paper_url":"http://arxiv.org/abs/1512.03385v1","paper_title":"Deep Residual Learning for Image Recognition","code":"https://github.com/tensorflow/models/tree/master/research/deeplab","n_code_links":484,"official":{"repos":["KaimingHe/resnet-1k-layers"],"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":254,"n_constructed":108,"n_ran_checked":163,"n_instrument":91,"n_unverified":123,"n_samples":377,"n_pointer_only_licence":193,"sample_list":"/paper/deep-residual-learning-for-image-recognition#ran","syntology_url":"https://syntology.ai/paper/1512.03385","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1512.03385"}}}},{"rank_in_archive_order":72,"model":"UNet++ (ResNet-101)","metrics":{"mIoU":"75.5"},"uses_additional_data":false,"paper_date":"2018-07-18","paper":"/paper/unet-a-nested-u-net-architecture-for-medical","paper_url":"http://arxiv.org/abs/1807.10165v1","paper_title":"UNet++: A Nested U-Net Architecture for Medical Image Segmentation","code":"https://github.com/qubvel/segmentation_models.pytorch","n_code_links":34,"official":{"repos":["MrGiovanni/Nested-UNet"],"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":18,"n_instrument":3,"n_unverified":7,"n_samples":28,"n_pointer_only_licence":3,"sample_list":"/paper/unet-a-nested-u-net-architecture-for-medical#ran","syntology_url":"https://syntology.ai/paper/1807.10165","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1807.10165"}}}},{"rank_in_archive_order":73,"model":"SqueezeNAS (LAT XLarge)","metrics":{"mIoU":"75.2%"},"uses_additional_data":true,"paper_date":"2019-08-05","paper":"/paper/squeezenas-fast-neural-architecture-search","paper_url":"https://arxiv.org/abs/1908.01748v2","paper_title":"SqueezeNAS: Fast neural architecture search for faster semantic segmentation","code":"https://github.com/ashaw596/squeezenas","n_code_links":1,"official":null,"syntology":{"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_samples":5,"n_pointer_only_licence":0,"sample_list":"/paper/squeezenas-fast-neural-architecture-search#ran","syntology_url":"https://syntology.ai/paper/1908.01748","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.01748"}}}},{"rank_in_archive_order":74,"model":"ReLICv2","metrics":{"mIoU":"75.2"},"uses_additional_data":false,"paper_date":"2022-01-13","paper":"/paper/pushing-the-limits-of-self-supervised-resnets","paper_url":"https://arxiv.org/abs/2201.05119v2","paper_title":"Pushing the limits of self-supervised ResNets: Can we outperform supervised learning without labels on ImageNet?","code":"https://github.com/google-deepmind/relicv2","n_code_links":1,"official":{"repos":["google-deepmind/relicv2"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":13,"n_constructed":0,"n_ran_checked":13,"n_instrument":0,"n_unverified":1,"n_samples":14,"n_pointer_only_licence":0,"sample_list":"/paper/pushing-the-limits-of-self-supervised-resnets#ran","syntology_url":"https://syntology.ai/paper/2201.05119","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.05119"}}}},{"rank_in_archive_order":75,"model":"CSFNet-1","metrics":{"FPS":"106.1 (3090)","mIoU":"74.73"},"uses_additional_data":false,"paper_date":"2024-07-01","paper":"/paper/csfnet-a-cosine-similarity-fusion-network-for","paper_url":"https://arxiv.org/abs/2407.01328v1","paper_title":"CSFNet: A Cosine Similarity Fusion Network for Real-Time RGB-X Semantic Segmentation of Driving Scenes","code":"https://github.com/Danial-Qashqai/CSFNet","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":76,"model":"GSCNN (ResNet-101)","metrics":{"mIoU":"74.7%"},"uses_additional_data":false,"paper_date":"2019-07-12","paper":"/paper/gated-scnn-gated-shape-cnns-for-semantic","paper_url":"https://arxiv.org/abs/1907.05740v1","paper_title":"Gated-SCNN: Gated Shape CNNs for Semantic Segmentation","code":"https://github.com/PaddlePaddle/PaddleSeg","n_code_links":4,"official":null,"syntology":null},{"rank_in_archive_order":77,"model":"BYOL","metrics":{"mIoU":"74.6"},"uses_additional_data":true,"paper_date":"2022-01-13","paper":"/paper/pushing-the-limits-of-self-supervised-resnets","paper_url":"https://arxiv.org/abs/2201.05119v2","paper_title":"Pushing the limits of self-supervised ResNets: Can we outperform supervised learning without labels on ImageNet?","code":"https://github.com/google-deepmind/relicv2","n_code_links":1,"official":{"repos":["google-deepmind/relicv2"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":13,"n_constructed":0,"n_ran_checked":13,"n_instrument":0,"n_unverified":1,"n_samples":14,"n_pointer_only_licence":0,"sample_list":"/paper/pushing-the-limits-of-self-supervised-resnets#ran","syntology_url":"https://syntology.ai/paper/2201.05119","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.05119"}}}},{"rank_in_archive_order":78,"model":"WASPnet (ours)","metrics":{"mIoU":"74%"},"uses_additional_data":false,"paper_date":"2019-12-06","paper":"/paper/waterfall-atrous-spatial-pooling-architecture","paper_url":"https://arxiv.org/abs/1912.03183v1","paper_title":"Waterfall Atrous Spatial Pooling Architecture for Efficient Semantic Segmentation","code":"https://github.com/bmartacho/WASP","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":79,"model":"SqueezeNAS (LAT Large)","metrics":{"mIoU":"73.6%"},"uses_additional_data":true,"paper_date":"2019-08-05","paper":"/paper/squeezenas-fast-neural-architecture-search","paper_url":"https://arxiv.org/abs/1908.01748v2","paper_title":"SqueezeNAS: Fast neural architecture search for faster semantic segmentation","code":"https://github.com/ashaw596/squeezenas","n_code_links":1,"official":null,"syntology":{"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_samples":5,"n_pointer_only_licence":0,"sample_list":"/paper/squeezenas-fast-neural-architecture-search#ran","syntology_url":"https://syntology.ai/paper/1908.01748","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.01748"}}}},{"rank_in_archive_order":80,"model":"FasterSeg","metrics":{"mIoU":"73.1%"},"uses_additional_data":false,"paper_date":"2019-12-23","paper":"/paper/fasterseg-searching-for-faster-real-time-1","paper_url":"https://arxiv.org/abs/1912.10917v2","paper_title":"FasterSeg: Searching for Faster Real-time Semantic Segmentation","code":"https://github.com/TAMU-VITA/FasterSeg","n_code_links":2,"official":{"repos":["TAMU-VITA/FasterSeg"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":11,"n_constructed":0,"n_ran_checked":9,"n_instrument":2,"n_unverified":2,"n_samples":13,"n_pointer_only_licence":2,"sample_list":"/paper/fasterseg-searching-for-faster-real-time-1#ran","syntology_url":"https://syntology.ai/paper/1912.10917","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.10917"}}}},{"rank_in_archive_order":81,"model":"GSCNN (ResNet-50)","metrics":{"mIoU":"73.0%"},"uses_additional_data":false,"paper_date":"2019-07-12","paper":"/paper/gated-scnn-gated-shape-cnns-for-semantic","paper_url":"https://arxiv.org/abs/1907.05740v1","paper_title":"Gated-SCNN: Gated Shape CNNs for Semantic Segmentation","code":"https://github.com/PaddlePaddle/PaddleSeg","n_code_links":4,"official":null,"syntology":null},{"rank_in_archive_order":82,"model":"Aerial-PASS (ResNet-18)","metrics":{"mIoU":"72.8%"},"uses_additional_data":false,"paper_date":"2021-05-15","paper":"/paper/aerial-pass-panoramic-annular-scene","paper_url":"https://arxiv.org/abs/2105.07209v1","paper_title":"Aerial-PASS: Panoramic Annular Scene Segmentation in Drone Videos","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":83,"model":"RFNet (ResNet-18)","metrics":{"mIoU":"72.5%"},"uses_additional_data":false,"paper_date":"2020-02-24","paper":"/paper/real-time-fusion-network-for-rgb-d-semantic","paper_url":"https://arxiv.org/abs/2002.10570v2","paper_title":"Real-time Fusion Network for RGB-D Semantic Segmentation Incorporating Unexpected Obstacle Detection for Road-driving Images","code":"https://github.com/AHupuJR/RFNet","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":84,"model":"ERFNet (PyTorch)","metrics":{"mIoU":"72.1%"},"uses_additional_data":false,"paper_date":"2017-10-09","paper":"/paper/erfnet-efficient-residual-factorized-convnet","paper_url":"https://ieeexplore.ieee.org/abstract/document/8063438","paper_title":"ERFNet: Efficient Residual Factorized ConvNet for Real-time Semantic Segmentation","code":"https://github.com/osmr/imgclsmob","n_code_links":13,"official":null,"syntology":null},{"rank_in_archive_order":85,"model":"SwaftNet (ResNet-18)","metrics":{"mIoU":"72.1%"},"uses_additional_data":false,"paper_date":"2019-09-17","paper":"/paper/ds-pass-detail-sensitive-panoramic-annular","paper_url":"https://arxiv.org/abs/1909.07721v2","paper_title":"DS-PASS: Detail-Sensitive Panoramic Annular Semantic Segmentation through SwaftNet for Surrounding Sensing","code":"https://github.com/elnino9ykl/DS-PASS","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":86,"model":"StreamDEQ (4 iterations)","metrics":{"FPS":"1.9","mIoU":"71.5"},"uses_additional_data":false,"paper_date":"2022-04-28","paper":"/paper/streaming-multiscale-deep-equilibrium-models","paper_url":"https://arxiv.org/abs/2204.13492v4","paper_title":"Representation Recycling for Streaming Video Analysis","code":"https://github.com/ufukertenli/streamdeq-code","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":87,"model":"Template-Based NAS-arch1","metrics":{"mIoU":"69.5%"},"uses_additional_data":false,"paper_date":"2019-04-04","paper":"/paper/template-based-automatic-search-of-compact","paper_url":"https://arxiv.org/abs/1904.02365v2","paper_title":"Template-Based Automatic Search of Compact Semantic Segmentation Architectures","code":"https://github.com/drsleep/nas-segm-pytorch","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":88,"model":"Fast-SCNN + Coarse + ImageNet","metrics":{"mIoU":"69.19"},"uses_additional_data":false,"paper_date":"2019-02-12","paper":"/paper/fast-scnn-fast-semantic-segmentation-network","paper_url":"http://arxiv.org/abs/1902.04502v1","paper_title":"Fast-SCNN: Fast Semantic Segmentation Network","code":"https://github.com/open-mmlab/mmsegmentation","n_code_links":24,"official":null,"syntology":{"n_ran":21,"n_constructed":0,"n_ran_checked":21,"n_instrument":0,"n_unverified":11,"n_samples":32,"n_pointer_only_licence":0,"sample_list":"/paper/fast-scnn-fast-semantic-segmentation-network#ran","syntology_url":"https://syntology.ai/paper/1902.04502","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.04502"}}}},{"rank_in_archive_order":89,"model":"LDFNet","metrics":{"mIoU":"68.48%"},"uses_additional_data":false,"paper_date":"2018-09-24","paper":"/paper/incorporating-luminance-depth-and-color","paper_url":"https://arxiv.org/abs/1809.09077v3","paper_title":"Incorporating Luminance, Depth and Color Information by a Fusion-based Network for Semantic Segmentation","code":"https://github.com/shangweihung/LDFNet","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":90,"model":"Template-Based NAS-arch0","metrics":{"mIoU":"68.1%"},"uses_additional_data":false,"paper_date":"2019-04-04","paper":"/paper/template-based-automatic-search-of-compact","paper_url":"https://arxiv.org/abs/1904.02365v2","paper_title":"Template-Based Automatic Search of Compact Semantic Segmentation Architectures","code":"https://github.com/drsleep/nas-segm-pytorch","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":91,"model":"SqueezeNAS (LAT Small)","metrics":{"mIoU":"68.0%"},"uses_additional_data":true,"paper_date":"2019-08-05","paper":"/paper/squeezenas-fast-neural-architecture-search","paper_url":"https://arxiv.org/abs/1908.01748v2","paper_title":"SqueezeNAS: Fast neural architecture search for faster semantic segmentation","code":"https://github.com/ashaw596/squeezenas","n_code_links":1,"official":null,"syntology":{"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_samples":5,"n_pointer_only_licence":0,"sample_list":"/paper/squeezenas-fast-neural-architecture-search#ran","syntology_url":"https://syntology.ai/paper/1908.01748","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.01748"}}}},{"rank_in_archive_order":92,"model":"ContextNet","metrics":{"mIoU":"65.9%"},"uses_additional_data":false,"paper_date":"2018-05-11","paper":"/paper/contextnet-exploring-context-and-detail-for","paper_url":"http://arxiv.org/abs/1805.04554v4","paper_title":"ContextNet: Exploring Context and Detail for Semantic Segmentation in Real-time","code":"https://github.com/osmr/imgclsmob","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":93,"model":"DiCENet","metrics":{"mIoU":"63.4"},"uses_additional_data":false,"paper_date":"2019-06-08","paper":"/paper/dicenet-dimension-wise-convolutions-for","paper_url":"https://arxiv.org/abs/1906.03516v3","paper_title":"DiCENet: Dimension-wise Convolutions for Efficient Networks","code":"https://github.com/osmr/imgclsmob","n_code_links":2,"official":{"repos":["sacmehta/EdgeNets"],"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/dicenet-dimension-wise-convolutions-for#ran","syntology_url":"https://syntology.ai/paper/1906.03516","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.03516"}}}},{"rank_in_archive_order":94,"model":"DCT-EDANet","metrics":{"mIoU":"61.6"},"uses_additional_data":false,"paper_date":"2019-07-23","paper":"/paper/exploring-semantic-segmentation-on-the-dct","paper_url":"https://arxiv.org/abs/1907.10015v2","paper_title":"Exploring Semantic Segmentation on the DCT Representation","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":95,"model":"StreamDEQ (2 iterations)","metrics":{"FPS":"2.9","mIoU":"57.9"},"uses_additional_data":false,"paper_date":"2022-04-28","paper":"/paper/streaming-multiscale-deep-equilibrium-models","paper_url":"https://arxiv.org/abs/2204.13492v4","paper_title":"Representation Recycling for Streaming Video Analysis","code":"https://github.com/ufukertenli/streamdeq-code","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":96,"model":"StreamDEQ (1 iterations)","metrics":{"FPS":"4.3","mIoU":"45.5"},"uses_additional_data":false,"paper_date":"2022-04-28","paper":"/paper/streaming-multiscale-deep-equilibrium-models","paper_url":"https://arxiv.org/abs/2204.13492v4","paper_title":"Representation Recycling for Streaming Video Analysis","code":"https://github.com/ufukertenli/streamdeq-code","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":97,"model":"MRFP+(Ours) Resnet50","metrics":{"mIoU":"42.4"},"uses_additional_data":false,"paper_date":"2023-11-30","paper":"/paper/mrfp-learning-generalizable-semantic","paper_url":"https://arxiv.org/abs/2311.18331v2","paper_title":"MRFP: Learning Generalizable Semantic Segmentation from Sim-2-Real with Multi-Resolution Feature Perturbation","code":"https://github.com/airl-iisc/MRFP","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":98,"model":"Resnet50","metrics":{"mIoU":"34.66"},"uses_additional_data":false,"paper_date":"2023-11-30","paper":"/paper/mrfp-learning-generalizable-semantic","paper_url":"https://arxiv.org/abs/2311.18331v2","paper_title":"MRFP: Learning Generalizable Semantic Segmentation from Sim-2-Real with Multi-Resolution Feature Perturbation","code":"https://github.com/airl-iisc/MRFP","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":99,"model":"SegFormer-B0","metrics":{"Validation mIoU":"76.2"},"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"}}}}],"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), 24 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 1,572 of the 8,888 were already full without this board, so if it was crowded out of them it is not counted), and 6 proposed a result; of those 6, 5 gave no cell that passed the extractor's own checks, 0 were rejected by the independent check, 0 await a verdict and 1 was 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":99,"metric_columns":3,"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":1572,"candidates":24,"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":6,"no_cell_passed_checks":5,"rejected_by_independent_check":0,"accepted_not_placed":0,"awaiting_verdict":0,"placed":1,"placed_entries_listed":1,"file_lines_unreadable_as_read":0,"since_line":"Since the archive (Syntology): 1 placed; 6 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":6,"shown_on_page":6,"no_cell_split":{"no_cell_passed_checks_in_ledger":5,"rows_refused_by_rule":5,"rows_no_cell_passed_checks":0},"rows":[{"arxiv_id":"2605.19289","outcome":"refused_by_rule","reason":"the column header qualifies the metric in a way the leaderboard does not"},{"arxiv_id":"2604.13761","outcome":"refused_by_rule","reason":"the column header qualifies the metric in a way the leaderboard does not; the row is an ablation variant, not the method itself"},{"arxiv_id":"2602.14134","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2601.17950","outcome":"refused_by_rule","reason":"the table reports a different split or setting than the leaderboard; the row label the model quoted is not the row's label"},{"arxiv_id":"2601.01167","outcome":"refused_by_rule","reason":"one configuration gave two values for one column"},{"arxiv_id":"2511.12594","outcome":"placed","reason":null}]},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":["mIoU"],"entries":[{"paper":"/paper/arxiv-2511-12594","paper_title":"Seg-VAR: Image Segmentation with Visual Autoregressive Modeling","arxiv_id":"2511.12594","model":"Seg-VAR","row_label":"Seg-VAR","configuration":null,"configuration_in_model":false,"configuration_not_shown_because":null,"values":{"mIoU":"85.82"},"date":"2025-11-16","month_from_arxiv_id":null,"where_in_paper":"Table 3, row “Seg-VAR”","table_label":"3","table_label_from":"the caption's own label","table_position_1based":3,"caption_head":"Table 3: Semantic Segmentation on the Cityscapes val split: UViM † [ 36 ] is…","caption_on_page":"shown","cells":[{"column":"mIoU","cell_text":"85.82","column_header":"mIoU","value":85.82,"table_index_0based":2,"row":17,"col":4}],"code":"repository linked, no samples harvested","samples_harvested":0,"sample_list":null,"syntology":{"syntology_url":"https://syntology.ai/paper/2511.12594","mcp":null}}]},"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":43,"rows_with_any_sample_ran":42,"rows_with_a_run_with_no_instrument_failure":39,"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":36,"rows_whose_official_repository_has_a_sample_that_ran":23,"rows_whose_official_repository_has_a_run_with_no_instrument_failure":19,"rows_community_repositories_only":6,"rows_runs_from_other_or_unrecorded_repositories":3,"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":31,"distinct_papers_with_a_run_with_no_instrument_failure":29,"samples_over_distinct_papers":{"n_ran":615,"n_constructed":160,"n_ran_checked":428,"n_instrument":187,"n_unverified":270,"n_samples":885,"n_pointer_only_licence":334,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":752,"n_constructed":188,"n_ran_checked":533,"n_instrument":219,"n_unverified":316,"n_samples":1068,"n_pointer_only_licence":380,"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":"50d21a82ab229bcf07430496a9e9540270e1d6f9f40f2f135d94094fb798fe16","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}