TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

SotA/Medical/Semantic Segmentation/PASCAL Context

Semantic Segmentation on PASCAL Context

Metric: mIoU (higher is better)

LeaderboardDataset
Loading chart...

Results

Submit a result
#Model↕mIoU▼Extra DataPaperDate↕Code
1VPNeXt71.1NoVPNeXt -- Rethinking Dense Decoding for Plain Vi...2025-02-23-
2PlainSeg (EVA-02-L)71NoMinimalist and High-Performance Semantic Segment...2023-10-19Code
3InternImage-H70.3NoInternImage: Exploring Large-Scale Vision Founda...2022-11-10Code
4RSSeg-ViT-L (BEiT pretrain)68.9NoRepresentation Separation for Semantic Segmentat...2022-12-28-
5ViT-Adapter-L (Mask2Former, BEiT pretrain)68.2NoVision Transformer Adapter for Dense Predictions2022-05-17Code
6ViT-Adapter-L (UperNet, BEiT pretrain)67.5NoVision Transformer Adapter for Dense Predictions2022-05-17Code
7RSSeg-ViT-L67.5NoRepresentation Separation for Semantic Segmentat...2022-12-28-
8SegViT (ours)65.3NoSegViT: Semantic Segmentation with Plain Vision ...2022-10-12Code
9CAA + CAR (ConvNeXt-Large + JPU)64.1NoCAR: Class-aware Regularizations for Semantic Se...2022-03-14Code
10SenFormer (Swin-L)64NoEfficient Self-Ensemble for Semantic Segmentation2021-11-26Code
11Sequential Ensemble (Segformer + HRNet)62.1NoSequential Ensembling for Semantic Segmentation2022-10-08-
12CAA + Simple decoder (Efficientnet-B7)60.5NoChannelized Axial Attention for Semantic Segment...2021-01-19Code
13DPT-Hybrid60.46NoVision Transformers for Dense Prediction2021-03-24Code
14CAA (Efficientnet-B7)60.1NoChannelized Axial Attention for Semantic Segment...2021-01-19Code
15HRNetV2 + OCR + RMI (PaddleClas pretrained)59.6NoSegmentation Transformer: Object-Contextual Repr...2019-09-24Code
16Seg-L-Mask/1659NoSegmenter: Transformer for Semantic Segmentation2021-05-12Code
17ResNeSt-26958.9NoResNeSt: Split-Attention Networks2020-04-19Code
18DEPICT-SA (ViT-L multi-scale)58.6NoRethinking Decoders for Transformer-based Semant...2024-11-05Code
19ResNeSt-20058.4NoResNeSt: Split-Attention Networks2020-04-19Code
20DEPICT-SA (ViT-L single-scale)57.9NoRethinking Decoders for Transformer-based Semant...2024-11-05Code
21CondNet(ResNest-101)57NoCondNet: Conditional Classifier for Scene Segmen...2021-09-21Code
22SenFormer (ResNet-101)56.6NoEfficient Self-Ensemble for Semantic Segmentation2021-11-26Code
23ResNeSt-10156.5NoResNeSt: Split-Attention Networks2020-04-19Code
24OCR (HRNetV2-W48)56.2NoSegmentation Transformer: Object-Contextual Repr...2019-09-24Code
25GPaCo (ResNet101)56.2NoGeneralized Parametric Contrastive Learning2022-09-26Code
26CondNet(ResNet-101)56NoCondNet: Conditional Classifier for Scene Segmen...2021-09-21Code
27SETR-MLA (16, 80k, MS)55.83NoRethinking Semantic Segmentation from a Sequence...2020-12-31Code
28DCNAS55.6NoDCNAS: Densely Connected Neural Architecture Sea...2020-03-26-
29DNL55.3NoDisentangled Non-Local Neural Networks2020-06-11Code
30HamNet (ResNet-101)55.2NoIs Attention Better Than Matrix Decomposition?2021-09-09Code
31CAA (ResNet-101)55NoChannelized Axial Attention for Semantic Segment...2021-01-19Code
32OCR (ResNet-101)54.8NoSegmentation Transformer: Object-Contextual Repr...2019-09-24Code
33SIW(Segformer-B5)54.2NoScaling up Multi-domain Semantic Segmentation wi...2022-02-04-
34CFNet (ResNet-101)54NoDeep High-Resolution Representation Learning for...2019-08-20Code
35CFNet (ResNet-101)54NoDeep High-Resolution Representation Learning for...2019-08-20Code
36HRNetV2 HRNetV2-W4854NoDeep High-Resolution Representation Learning for...2019-08-20Code
37CPN(ResNet-101)53.9NoContext Prior for Scene Segmentation2020-04-03Code
38LaU-regression-loss (ResNet-101)53.9NoLocation-aware Upsampling for Semantic Segmentat...2019-11-13Code
39DGCNet (MS, ResNet-101)53.7NoDual Graph Convolutional Network for Semantic Se...2019-09-13Code
40BFP53.6NoBoundary-Aware Feature Propagation for Scene Seg...2019-08-31Code
41SVCNet (ResNet-101)53.2NoSemantic Correlation Promoted Shape-Variant Cont...2019-09-05Code
42Joint Pyramid Upsampling + EncNet53.1NoFastFCN: Rethinking Dilated Convolution in the B...2019-03-28Code
43EMANet53.1NoExpectation-Maximization Attention Networks for ...2019-07-31Code
44Asymmetric ALNN52.8NoAsymmetric Non-local Neural Networks for Semanti...2019-08-21Code
45CASSOD52.76NoCASSOD-Net: Cascaded and Separable Structures of...2021-04-29-
46DANet (ResNet-101)52.6NoDual Attention Network for Scene Segmentation2018-09-09Code
47ICM52.6No--Code
48DUpsampling52.5NoDecoders Matter for Semantic Segmentation: Data-...2019-03-05-
49EncNet (ResNet-101)51.7NoContext Encoding for Semantic Segmentation2018-03-23Code
50CFNet (ResNet-50)51.5No--Code
51ResNet-3848.1NoWider or Deeper: Revisiting the ResNet Model for...2016-11-30Code
52PSPNet (ResNet-101)47.8NoPyramid Scene Parsing Network2016-12-04Code
53RefineNet47.3NoRefineNet: Multi-Path Refinement Networks for Hi...2016-11-20Code
54DeepLabV245.7NoDeepLab: Semantic Image Segmentation with Deep C...2016-06-02Code
55VeryDeep44.5NoBridging Category-level and Instance-level Seman...2016-05-23-
56Piecewise43.3NoEfficient piecewise training of deep structured ...2015-04-04-
57Dilated-FCN2s42.6NoEfficient Yet Deep Convolutional Neural Networks...2017-07-26Code
58HO CRF41.3NoHigher Order Conditional Random Fields in Deep N...2015-11-25Code
59BoxSup40.5NoBoxSup: Exploiting Bounding Boxes to Supervise C...2015-03-05-
60ParseNet40.4NoParseNet: Looking Wider to See Better2015-06-15Code
61CRF-RNN39.3NoConditional Random Fields as Recurrent Neural Ne...2015-02-11Code
62FCN-8s37.8NoFully Convolutional Networks for Semantic Segmen...2014-11-14Code
63CFM34.4NoConvolutional Feature Masking for Joint Object a...2014-12-03Code
64RBE2E32.5NoRegion-based semantic segmentation with end-to-e...2016-07-26Code
65SegCLIP24.7NoSegCLIP: Patch Aggregation with Learnable Center...2022-11-27Code