Metric: Test Score (higher is better)
| # | Model↕ | Test Score▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | Swin-L (UperNet, ImageNet-22k pretrain) | 62.8 | No | Swin Transformer: Hierarchical Vision Transforme... | 2021-03-25 | Code |
| 2 | PyConvSegNet-152 | 56.52 | No | Pyramidal Convolution: Rethinking Convolutional ... | 2020-06-20 | Code |
| 3 | LaU-offset-loss | 56.41 | No | Location-aware Upsampling for Semantic Segmentat... | 2019-11-13 | Code |
| 4 | LaU-regression-loss | 56.32 | No | Location-aware Upsampling for Semantic Segmentat... | 2019-11-13 | Code |
| 5 | EncNet + JPU | 55.84 | No | FastFCN: Rethinking Dilated Convolution in the B... | 2019-03-28 | Code |
| 6 | EncNet | 55.67 | No | Context Encoding for Semantic Segmentation | 2018-03-23 | Code |
| 7 | PSPNet | 55.38 | No | Pyramid Scene Parsing Network | 2016-12-04 | Code |