{"url":"/sota/semantic-segmentation-on-pascal-context","task":{"name":"Semantic Segmentation","url":"/task/semantic-segmentation","note":null},"dataset":{"name":"PASCAL Context","url":"/dataset/pascal-context"},"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","Mean Accuracy","Pixel Accuracy"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"mIoU":null,"Mean Accuracy":"higher","Pixel Accuracy":"higher"}},"counts":{"rows":66,"rows_with_code":55,"rows_with_paper_page":66,"rows_dated":66,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"VPNeXt","metrics":{"mIoU":"71.1"},"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,"syntology":null},{"rank_in_archive_order":2,"model":"PlainSeg (EVA-02-L)","metrics":{"mIoU":"71.0"},"uses_additional_data":false,"paper_date":"2023-10-19","paper":"/paper/minimalist-and-high-performance-semantic","paper_url":"https://arxiv.org/abs/2310.12755v1","paper_title":"Minimalist and High-Performance Semantic Segmentation with Plain Vision Transformers","code":"https://github.com/ydhonghit/plainseg","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"InternImage-H","metrics":{"mIoU":"70.3"},"uses_additional_data":false,"paper_date":"2022-11-10","paper":"/paper/internimage-exploring-large-scale-vision","paper_url":"https://arxiv.org/abs/2211.05778v4","paper_title":"InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions","code":"https://github.com/opengvlab/internimage","n_code_links":3,"syntology":{"n_ran":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":4,"model":"RSSeg-ViT-L (BEiT pretrain)","metrics":{"mIoU":"68.9"},"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,"syntology":null},{"rank_in_archive_order":5,"model":"ViT-Adapter-L (Mask2Former, BEiT pretrain)","metrics":{"mIoU":"68.2"},"uses_additional_data":false,"paper_date":"2022-05-17","paper":"/paper/vision-transformer-adapter-for-dense","paper_url":"https://arxiv.org/abs/2205.08534v4","paper_title":"Vision Transformer Adapter for Dense Predictions","code":"https://github.com/czczup/vit-adapter","n_code_links":2,"syntology":null},{"rank_in_archive_order":6,"model":"ViT-Adapter-L (UperNet, BEiT pretrain)","metrics":{"mIoU":"67.5"},"uses_additional_data":false,"paper_date":"2022-05-17","paper":"/paper/vision-transformer-adapter-for-dense","paper_url":"https://arxiv.org/abs/2205.08534v4","paper_title":"Vision Transformer Adapter for Dense Predictions","code":"https://github.com/czczup/vit-adapter","n_code_links":2,"syntology":null},{"rank_in_archive_order":7,"model":"RSSeg-ViT-L","metrics":{"mIoU":"67.5"},"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,"syntology":null},{"rank_in_archive_order":8,"model":"SegViT (ours)","metrics":{"mIoU":"65.3"},"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,"syntology":null},{"rank_in_archive_order":9,"model":"CAA + CAR (ConvNeXt-Large + JPU)","metrics":{"mIoU":"64.1"},"uses_additional_data":false,"paper_date":"2022-03-14","paper":"/paper/car-class-aware-regularizations-for-semantic-1","paper_url":"https://arxiv.org/abs/2203.07160v2","paper_title":"CAR: Class-aware Regularizations for Semantic Segmentation","code":"https://github.com/edwardyehuang/CAR","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":4,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":10,"model":"SenFormer (Swin-L)","metrics":{"mIoU":"64.0"},"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,"syntology":null},{"rank_in_archive_order":11,"model":"Sequential Ensemble (Segformer + HRNet)","metrics":{"mIoU":"62.1"},"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,"syntology":null},{"rank_in_archive_order":12,"model":"CAA + Simple decoder (Efficientnet-B7)","metrics":{"mIoU":"60.5"},"uses_additional_data":false,"paper_date":"2021-01-19","paper":"/paper/caa-channelized-axial-attention-for-semantic","paper_url":"https://arxiv.org/abs/2101.07434v5","paper_title":"Channelized Axial Attention for Semantic Segmentation -- Considering Channel Relation within Spatial Attention for Semantic Segmentation","code":"https://github.com/edwardyehuang/CAA","n_code_links":1,"syntology":null},{"rank_in_archive_order":13,"model":"DPT-Hybrid","metrics":{"mIoU":"60.46"},"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,"syntology":{"n_ran":54,"n_unverified":62,"n_samples":116,"n_pointer_only_licence":15}},{"rank_in_archive_order":14,"model":"CAA (Efficientnet-B7)","metrics":{"mIoU":"60.1"},"uses_additional_data":false,"paper_date":"2021-01-19","paper":"/paper/caa-channelized-axial-attention-for-semantic","paper_url":"https://arxiv.org/abs/2101.07434v5","paper_title":"Channelized Axial Attention for Semantic Segmentation -- Considering Channel Relation within Spatial Attention for Semantic Segmentation","code":"https://github.com/edwardyehuang/CAA","n_code_links":1,"syntology":null},{"rank_in_archive_order":15,"model":"HRNetV2 + OCR + RMI (PaddleClas pretrained)","metrics":{"mIoU":"59.6"},"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,"syntology":{"n_ran":4,"n_unverified":5,"n_samples":9,"n_pointer_only_licence":1}},{"rank_in_archive_order":16,"model":"Seg-L-Mask/16","metrics":{"mIoU":"59.0"},"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,"syntology":{"n_ran":0,"n_unverified":7,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":17,"model":"ResNeSt-269","metrics":{"mIoU":"58.9"},"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,"syntology":{"n_ran":8,"n_unverified":40,"n_samples":48,"n_pointer_only_licence":23}},{"rank_in_archive_order":18,"model":"DEPICT-SA (ViT-L multi-scale)","metrics":{"mIoU":"58.6"},"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,"syntology":null},{"rank_in_archive_order":19,"model":"ResNeSt-200","metrics":{"mIoU":"58.4"},"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,"syntology":{"n_ran":8,"n_unverified":40,"n_samples":48,"n_pointer_only_licence":23}},{"rank_in_archive_order":20,"model":"DEPICT-SA (ViT-L single-scale)","metrics":{"mIoU":"57.9"},"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,"syntology":null},{"rank_in_archive_order":21,"model":"CondNet(ResNest-101)","metrics":{"mIoU":"57"},"uses_additional_data":false,"paper_date":"2021-09-21","paper":"/paper/condnet-conditional-classifier-for-scene","paper_url":"https://arxiv.org/abs/2109.10322v1","paper_title":"CondNet: Conditional Classifier for Scene Segmentation","code":"https://github.com/sithu31296/semantic-segmentation","n_code_links":2,"syntology":null},{"rank_in_archive_order":22,"model":"SenFormer (ResNet-101)","metrics":{"mIoU":"56.6"},"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,"syntology":null},{"rank_in_archive_order":23,"model":"ResNeSt-101","metrics":{"mIoU":"56.5"},"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,"syntology":{"n_ran":8,"n_unverified":40,"n_samples":48,"n_pointer_only_licence":23}},{"rank_in_archive_order":24,"model":"OCR (HRNetV2-W48)","metrics":{"mIoU":"56.2"},"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,"syntology":{"n_ran":4,"n_unverified":5,"n_samples":9,"n_pointer_only_licence":1}},{"rank_in_archive_order":25,"model":"GPaCo (ResNet101)","metrics":{"mIoU":"56.2"},"uses_additional_data":false,"paper_date":"2022-09-26","paper":"/paper/generalized-parametric-contrastive-learning","paper_url":"https://arxiv.org/abs/2209.12400v2","paper_title":"Generalized Parametric Contrastive Learning","code":"https://github.com/dvlab-research/parametric-contrastive-learning","n_code_links":4,"syntology":null},{"rank_in_archive_order":26,"model":"CondNet(ResNet-101)","metrics":{"mIoU":"56.0"},"uses_additional_data":false,"paper_date":"2021-09-21","paper":"/paper/condnet-conditional-classifier-for-scene","paper_url":"https://arxiv.org/abs/2109.10322v1","paper_title":"CondNet: Conditional Classifier for Scene Segmentation","code":"https://github.com/sithu31296/semantic-segmentation","n_code_links":2,"syntology":null},{"rank_in_archive_order":27,"model":"SETR-MLA (16, 80k, MS)","metrics":{"mIoU":"55.83"},"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,"syntology":null},{"rank_in_archive_order":28,"model":"DCNAS","metrics":{"mIoU":"55.6"},"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,"syntology":null},{"rank_in_archive_order":29,"model":"DRAN(ResNet-101)","metrics":{"mIoU":"55.4%"},"uses_additional_data":false,"paper_date":"2020-08-05","paper":"/paper/scene-segmentation-with-dual-relation-aware","paper_url":"https://ieeexplore.ieee.org/document/9154612","paper_title":"Scene Segmentation with Dual Relation-aware Attention Network","code":"https://github.com/junfu1115/DRAN","n_code_links":1,"syntology":null},{"rank_in_archive_order":30,"model":"DNL","metrics":{"mIoU":"55.3"},"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,"syntology":{"n_ran":1,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":31,"model":"HamNet (ResNet-101)","metrics":{"mIoU":"55.2"},"uses_additional_data":false,"paper_date":"2021-09-09","paper":"/paper/is-attention-better-than-matrix-decomposition-1","paper_url":"https://arxiv.org/abs/2109.04553v2","paper_title":"Is Attention Better Than Matrix Decomposition?","code":"https://github.com/Gsunshine/Enjoy-Hamburger","n_code_links":3,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":32,"model":"CAA (ResNet-101)","metrics":{"mIoU":"55.0"},"uses_additional_data":false,"paper_date":"2021-01-19","paper":"/paper/caa-channelized-axial-attention-for-semantic","paper_url":"https://arxiv.org/abs/2101.07434v5","paper_title":"Channelized Axial Attention for Semantic Segmentation -- Considering Channel Relation within Spatial Attention for Semantic Segmentation","code":"https://github.com/edwardyehuang/CAA","n_code_links":1,"syntology":null},{"rank_in_archive_order":33,"model":"OCR (ResNet-101)","metrics":{"mIoU":"54.8"},"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,"syntology":{"n_ran":4,"n_unverified":5,"n_samples":9,"n_pointer_only_licence":1}},{"rank_in_archive_order":34,"model":"SIW(Segformer-B5)","metrics":{"mIoU":"54.2"},"uses_additional_data":false,"paper_date":"2022-02-04","paper":"/paper/the-devil-is-in-the-labels-semantic","paper_url":"https://arxiv.org/abs/2202.02002v2","paper_title":"Scaling up Multi-domain Semantic Segmentation with Sentence Embeddings","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":35,"model":"CFNet (ResNet-101)","metrics":{"mIoU":"54.0"},"uses_additional_data":false,"paper_date":"2019-06-01","paper":"/paper/co-occurrent-features-in-semantic","paper_url":"http://openaccess.thecvf.com/content_CVPR_2019/html/Zhang_Co-Occurrent_Features_in_Semantic_Segmentation_CVPR_2019_paper.html","paper_title":"Co-Occurrent Features in Semantic Segmentation","code":"https://github.com/zhanghang1989/PyTorch-Encoding","n_code_links":2,"syntology":null},{"rank_in_archive_order":36,"model":"CFNet (ResNet-101)","metrics":{"mIoU":"54.0"},"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,"syntology":{"n_ran":3,"n_unverified":31,"n_samples":34,"n_pointer_only_licence":16}},{"rank_in_archive_order":37,"model":"HRNetV2 HRNetV2-W48","metrics":{"mIoU":"54"},"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,"syntology":{"n_ran":3,"n_unverified":31,"n_samples":34,"n_pointer_only_licence":16}},{"rank_in_archive_order":38,"model":"CPN(ResNet-101)","metrics":{"mIoU":"53.9"},"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,"syntology":null},{"rank_in_archive_order":39,"model":"LaU-regression-loss (ResNet-101)","metrics":{"mIoU":"53.9"},"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,"syntology":null},{"rank_in_archive_order":40,"model":"DGCNet (MS, ResNet-101)","metrics":{"mIoU":"53.7"},"uses_additional_data":false,"paper_date":"2019-09-13","paper":"/paper/dual-graph-convolutional-network-for-semantic","paper_url":"https://arxiv.org/abs/1909.06121v3","paper_title":"Dual Graph Convolutional Network for Semantic Segmentation","code":"https://github.com/lxtGH/GALD-DGCNet","n_code_links":6,"syntology":null},{"rank_in_archive_order":41,"model":"BFP","metrics":{"mIoU":"53.6"},"uses_additional_data":false,"paper_date":"2019-08-31","paper":"/paper/boundary-aware-feature-propagation-for-scene","paper_url":"https://arxiv.org/abs/1909.00179v1","paper_title":"Boundary-Aware Feature Propagation for Scene Segmentation","code":"https://github.com/henghuiding/BFP","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":10,"n_samples":11,"n_pointer_only_licence":0}},{"rank_in_archive_order":42,"model":"SVCNet (ResNet-101)","metrics":{"mIoU":"53.2"},"uses_additional_data":false,"paper_date":"2019-09-05","paper":"/paper/semantic-correlation-promoted-shape-variant-1","paper_url":"https://arxiv.org/abs/1909.02651v1","paper_title":"Semantic Correlation Promoted Shape-Variant Context for Segmentation","code":"https://github.com/henghuiding/SVC","n_code_links":1,"syntology":null},{"rank_in_archive_order":43,"model":"Joint Pyramid Upsampling + EncNet","metrics":{"mIoU":"53.1"},"uses_additional_data":false,"paper_date":"2019-03-28","paper":"/paper/fastfcn-rethinking-dilated-convolution-in-the","paper_url":"http://arxiv.org/abs/1903.11816v1","paper_title":"FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation","code":"https://github.com/PaddlePaddle/PaddleSeg","n_code_links":12,"syntology":null},{"rank_in_archive_order":44,"model":"EMANet","metrics":{"mIoU":"53.1"},"uses_additional_data":false,"paper_date":"2019-07-31","paper":"/paper/expectation-maximization-attention-networks","paper_url":"https://arxiv.org/abs/1907.13426v2","paper_title":"Expectation-Maximization Attention Networks for Semantic Segmentation","code":"https://github.com/open-mmlab/mmsegmentation","n_code_links":5,"syntology":null},{"rank_in_archive_order":45,"model":"Asymmetric ALNN","metrics":{"mIoU":"52.8"},"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,"syntology":{"n_ran":0,"n_unverified":3,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":46,"model":"CASSOD","metrics":{"mIoU":"52.76"},"uses_additional_data":false,"paper_date":"2021-04-29","paper":"/paper/cassod-net-cascaded-and-separable-structures","paper_url":"https://arxiv.org/abs/2104.14126v1","paper_title":"CASSOD-Net: Cascaded and Separable Structures of Dilated Convolution for Embedded Vision Systems and Applications","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":47,"model":"DANet (ResNet-101)","metrics":{"mIoU":"52.6"},"uses_additional_data":false,"paper_date":"2018-09-09","paper":"/paper/dual-attention-network-for-scene-segmentation","paper_url":"http://arxiv.org/abs/1809.02983v4","paper_title":"Dual Attention Network for Scene Segmentation","code":"https://github.com/xmu-xiaoma666/External-Attention-pytorch","n_code_links":12,"syntology":{"n_ran":0,"n_unverified":7,"n_samples":7,"n_pointer_only_licence":5}},{"rank_in_archive_order":48,"model":"ICM","metrics":{"mIoU":"52.60"},"uses_additional_data":false,"paper_date":"2019-06-01","paper":"/paper/scene-parsing-via-integrated-classification","paper_url":"http://openaccess.thecvf.com/content_CVPR_2019/html/Shi_Scene_Parsing_via_Integrated_Classification_Model_and_Variance-Based_Regularization_CVPR_2019_paper.html","paper_title":"Scene Parsing via Integrated Classification Model and Variance-Based Regularization","code":"https://github.com/shihengcan/ICM-matcaffe","n_code_links":1,"syntology":null},{"rank_in_archive_order":49,"model":"DUpsampling","metrics":{"mIoU":"52.5"},"uses_additional_data":false,"paper_date":"2019-03-05","paper":"/paper/decoders-matter-for-semantic-segmentation","paper_url":"http://arxiv.org/abs/1903.02120v3","paper_title":"Decoders Matter for Semantic Segmentation: Data-Dependent Decoding Enables Flexible Feature Aggregation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":50,"model":"EncNet (ResNet-101)","metrics":{"mIoU":"51.7"},"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,"syntology":{"n_ran":1,"n_unverified":7,"n_samples":8,"n_pointer_only_licence":7}},{"rank_in_archive_order":51,"model":"CFNet (ResNet-50)","metrics":{"mIoU":"51.5"},"uses_additional_data":false,"paper_date":"2019-06-01","paper":"/paper/co-occurrent-features-in-semantic","paper_url":"http://openaccess.thecvf.com/content_CVPR_2019/html/Zhang_Co-Occurrent_Features_in_Semantic_Segmentation_CVPR_2019_paper.html","paper_title":"Co-Occurrent Features in Semantic Segmentation","code":"https://github.com/zhanghang1989/PyTorch-Encoding","n_code_links":2,"syntology":null},{"rank_in_archive_order":52,"model":"ResNet-38","metrics":{"mIoU":"48.1"},"uses_additional_data":false,"paper_date":"2016-11-30","paper":"/paper/wider-or-deeper-revisiting-the-resnet-model","paper_url":"http://arxiv.org/abs/1611.10080v1","paper_title":"Wider or Deeper: Revisiting the ResNet Model for Visual Recognition","code":"https://github.com/itijyou/ademxapp","n_code_links":3,"syntology":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":53,"model":"PSPNet (ResNet-101)","metrics":{"mIoU":"47.8"},"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,"syntology":{"n_ran":7,"n_unverified":22,"n_samples":29,"n_pointer_only_licence":5}},{"rank_in_archive_order":54,"model":"RefineNet","metrics":{"mIoU":"47.3"},"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,"syntology":{"n_ran":1,"n_unverified":6,"n_samples":7,"n_pointer_only_licence":1}},{"rank_in_archive_order":55,"model":"DeepLabV2","metrics":{"mIoU":"45.7"},"uses_additional_data":false,"paper_date":"2016-06-02","paper":"/paper/deeplab-semantic-image-segmentation-with-deep","paper_url":"http://arxiv.org/abs/1606.00915v2","paper_title":"DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs","code":"https://github.com/tensorflow/models/tree/master/research/deeplab","n_code_links":47,"syntology":{"n_ran":28,"n_unverified":35,"n_samples":63,"n_pointer_only_licence":16}},{"rank_in_archive_order":56,"model":"VeryDeep","metrics":{"mIoU":"44.5"},"uses_additional_data":false,"paper_date":"2016-05-23","paper":"/paper/bridging-category-level-and-instance-level","paper_url":"http://arxiv.org/abs/1605.06885v1","paper_title":"Bridging Category-level and Instance-level Semantic Image Segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":57,"model":"Piecewise","metrics":{"mIoU":"43.3"},"uses_additional_data":false,"paper_date":"2015-04-04","paper":"/paper/efficient-piecewise-training-of-deep","paper_url":"http://arxiv.org/abs/1504.01013v4","paper_title":"Efficient piecewise training of deep structured models for semantic segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":58,"model":"Dilated-FCN2s","metrics":{"mIoU":"42.6"},"uses_additional_data":false,"paper_date":"2017-07-26","paper":"/paper/efficient-yet-deep-convolutional-neural","paper_url":"http://arxiv.org/abs/1707.08254v3","paper_title":"Efficient Yet Deep Convolutional Neural Networks for Semantic Segmentation","code":"https://github.com/SharifAmit/DilatedFCNSegmentation","n_code_links":1,"syntology":null},{"rank_in_archive_order":59,"model":"HO CRF","metrics":{"mIoU":"41.3"},"uses_additional_data":false,"paper_date":"2015-11-25","paper":"/paper/higher-order-conditional-random-fields-in","paper_url":"http://arxiv.org/abs/1511.08119v4","paper_title":"Higher Order Conditional Random Fields in Deep Neural Networks","code":"https://github.com/torrvision/caffe-tvg","n_code_links":1,"syntology":null},{"rank_in_archive_order":60,"model":"BoxSup","metrics":{"mIoU":"40.5"},"uses_additional_data":false,"paper_date":"2015-03-05","paper":"/paper/boxsup-exploiting-bounding-boxes-to-supervise","paper_url":"http://arxiv.org/abs/1503.01640v2","paper_title":"BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":61,"model":"ParseNet","metrics":{"mIoU":"40.4"},"uses_additional_data":false,"paper_date":"2015-06-15","paper":"/paper/parsenet-looking-wider-to-see-better","paper_url":"http://arxiv.org/abs/1506.04579v2","paper_title":"ParseNet: Looking Wider to See Better","code":"https://github.com/tensorflow/models/tree/master/research/deeplab","n_code_links":4,"syntology":null},{"rank_in_archive_order":62,"model":"CRF-RNN","metrics":{"mIoU":"39.3"},"uses_additional_data":false,"paper_date":"2015-02-11","paper":"/paper/conditional-random-fields-as-recurrent-neural-1","paper_url":"http://arxiv.org/abs/1502.03240v3","paper_title":"Conditional Random Fields as Recurrent Neural Networks","code":"https://github.com/torrvision/crfasrnn","n_code_links":6,"syntology":{"n_ran":1,"n_unverified":7,"n_samples":8,"n_pointer_only_licence":2}},{"rank_in_archive_order":63,"model":"FCN-8s","metrics":{"mIoU":"37.8"},"uses_additional_data":false,"paper_date":"2014-11-14","paper":"/paper/fully-convolutional-networks-for-semantic-1","paper_url":"http://arxiv.org/abs/1411.4038v2","paper_title":"Fully Convolutional Networks for Semantic Segmentation","code":"https://github.com/pochih/fcn-pytorch","n_code_links":51,"syntology":{"n_ran":3,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":4}},{"rank_in_archive_order":64,"model":"CFM","metrics":{"mIoU":"34.4"},"uses_additional_data":false,"paper_date":"2014-12-03","paper":"/paper/convolutional-feature-masking-for-joint","paper_url":"http://arxiv.org/abs/1412.1283v4","paper_title":"Convolutional Feature Masking for Joint Object and Stuff Segmentation","code":"https://github.com/daijifeng001/MNC","n_code_links":1,"syntology":null},{"rank_in_archive_order":65,"model":"RBE2E","metrics":{"Mean Accuracy":"49.9","Pixel Accuracy":"62.4","mIoU":"32.5"},"uses_additional_data":false,"paper_date":"2016-07-26","paper":"/paper/region-based-semantic-segmentation-with-end","paper_url":"http://arxiv.org/abs/1607.07671v1","paper_title":"Region-based semantic segmentation with end-to-end training","code":"https://github.com/nightrome/matconvnet-calvin","n_code_links":1,"syntology":null},{"rank_in_archive_order":66,"model":"SegCLIP","metrics":{"mIoU":"24.7"},"uses_additional_data":false,"paper_date":"2022-11-27","paper":"/paper/segclip-patch-aggregation-with-learnable","paper_url":"https://arxiv.org/abs/2211.14813v2","paper_title":"SegCLIP: Patch Aggregation with Learnable Centers for Open-Vocabulary Semantic Segmentation","code":"https://github.com/arrowluo/segclip","n_code_links":1,"syntology":null}],"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,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,795 of the 9,581 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9581,"papers_checked":6795,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":2785},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":["mIoU"],"entries":[{"paper":"/paper/arxiv-2508-20376","paper_title":"Enhancing Mamba Decoder with Bidirectional Interaction in Multi-Task Dense Prediction","arxiv_id":"2508.20376","model":"BIM(Ours) · Semseg","row_label":"BIM(Ours)","configuration":"Semseg","configuration_in_model":true,"configuration_not_shown_because":null,"values":{"mIoU":"81.25"},"date":"2025-08-28","month_from_arxiv_id":null,"where_in_paper":"Table 2, row “BIM(Ours)”","table_label":"2","table_label_from":"the caption's own label","table_position_1based":2,"caption_head":"Table 2 : Quantitative comparison with other […] methods on…","cells":[{"column":"mIoU","cell_text":"81.25","column_header":"Semseg / mIoU \\uparrow","value":81.25,"table_index_0based":1,"row":16,"col":1}],"code":"repository linked, no samples harvested"}]},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N 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).","rows_with_graph_line":24,"rows_with_any_sample_ran":19,"distinct_papers_with_graph_line":19,"distinct_papers_with_any_sample_ran":14,"samples_over_distinct_papers":{"n_ran":117,"n_unverified":253,"n_samples":370,"n_pointer_only_licence":100,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":144,"n_unverified":374,"n_samples":518,"n_pointer_only_licence":164,"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"}}}