Semantic Segmentation on SYNTHIA to Cityscapes 16 classes (test)
70.43mIoUMTL target
Evaluation Results
| Method | Links | ||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| MTL targetArchitecture=Multi-Task Learning, Strategy=Oracle (Target Labels)2022.06 | 70.43 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| STL targetArchitecture=Single-Task Learning, Strategy=Oracle (Target Labels)2022.06 | 67.93 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Ours (best mIoU)Depth=true, Protocol=EP12021.05 | 44.9 | 88.1 | 39.1 | 81.8 | 19.6 | 0.7 | 30.2 | 7.7 | 13.8 | 82.4 | 83 | 60.2 | 22 | 81.7 | 47.6 | 24.8 | 35 | 51.3 | — | — | — | — | — | — | |
| Ours (confidence)Depth=true, Protocol=EP1, Note=mean over five runs2021.05 | 44.3 | 85.5 | 40.6 | 80 | 16.5 | 0.73 | 28.5 | 7.2 | 11.7 | 80.7 | 82.4 | 60.2 | 22.2 | 79.1 | 47.2 | 26 | 40.6 | 51 | — | — | — | — | — | — | |
| DADADepth=true, Protocol=EP12021.05 | 42.6 | 89.2 | 44.8 | 81.4 | 6.8 | 0.3 | 26.2 | 8.6 | 11.1 | 81.8 | 84 | 54.7 | 19.3 | 79.7 | 40.7 | 14 | 38.8 | 49.8 | — | — | — | — | — | — | |
| AdventDepth=false, Protocol=EP12021.05 | 40.8 | 87 | 44.1 | 79.7 | 9.6 | 0.6 | 24.3 | 4.8 | 7.2 | 80.1 | 83.6 | 56.4 | 23.7 | 72.7 | 32.6 | 12.8 | 33.7 | 47.6 | — | — | — | — | — | — | |
| mTEB (Ours)Architecture=Multi-Task Learning with mTEB, Strategy=Unsupervised Domain Adaptation2022.06 | 37.93 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| STL-UDAArchitecture=Single-Task Learning, Strategy=Unsupervised Domain Adaptation2022.06 | 37.55 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| SPIGANDepth=true, Protocol=EP12021.05 | 36.8 | 71.1 | 29.8 | 71.4 | 3.7 | 0.3 | 33.2 | 6.4 | 15.6 | 81.2 | 78.9 | 52.7 | 13.1 | 75.9 | 25.5 | 10 | 20.5 | 42.4 | — | — | — | — | — | — | |
| SPIGAN-no-PIDepth=false, Protocol=EP12021.05 | 35.8 | 69.5 | 29.4 | 68.7 | 4.4 | 0.3 | 32.4 | 5.8 | 15 | 81 | 78.7 | 52.2 | 13.1 | 72.8 | 23.6 | 7.9 | 18.7 | 41.2 | — | — | — | — | — | — | |
| STL sourceArchitecture=Single-Task Learning, Strategy=Source only2022.06 | 35.63 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MTL-UDAArchitecture=Multi-Task Learning, Strategy=Unsupervised Domain Adaptation2022.06 | 16.71 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MTL sourceArchitecture=Multi-Task Learning, Strategy=Source only2022.06 | 15.32 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| AdaptPatchDepth=false, Protocol=EP12021.05 | — | 82.2 | 39.4 | 79.4 | — | — | 6.5 | — | 10.8 | 77.8 | 82 | 54.9 | 21.1 | 67.7 | 30.7 | 17.8 | 32.2 | 46.3 | — | — | — | — | — | — | |
| AdaptSegBackbone=VGG-16, Segmentation Model=FCN-8s2021.10 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 17 | 20.5 | 21.6 | 21.6 | 20 | 20.2 | |
| AdaptSegnetDepth=false, Protocol=EP12021.05 | — | 79.2 | 37.2 | 78.8 | — | — | 9.9 | — | 10.5 | 78.2 | 80.5 | 53.5 | 19.6 | 67 | 29.5 | 21.6 | 31.3 | 45.9 | — | — | — | — | — | — | |
| AdventBackbone=VGG-16, Segmentation Model=FCN-8s2021.10 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 17.7 | 19.9 | 20.2 | 20.5 | 19.3 | 19.6 | |
| CBSTBackbone=VGG-16, Segmentation Model=FCN-8s2021.10 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 16.2 | 19.6 | 20.1 | 20.3 | 18.9 | 19.1 | |
| CLANDepth=false, Protocol=EP12021.05 | — | 81.3 | 37 | 80.1 | — | — | 16.1 | 13.7 | 78.2 | 81.5 | 53.4 | 21.2 | 73 | 32.9 | 22.6 | 30.7 | — | 47.8 | — | — | — | — | — | — | |
| CRSTBackbone=VGG-16, Segmentation Model=FCN-8s2021.10 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 16.3 | 19.9 | 20.3 | 20.5 | 19.1 | 19.3 | |
| DHABackbone=VGG-16, Segmentation Model=FCN-8s2021.10 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 18.8 | 21.2 | 23.6 | 23.6 | 21.5 | 21.8 | |
| Source OnlyBackbone=VGG-16, Segmentation Model=FCN-8s2021.10 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 16.3 | 18.8 | 19.4 | 19.5 | 18.4 | 18.5 |