Semantic Segmentation on SYNTHIA to Cityscapes
93.3Road IoUCorDA
Evaluation results
| Method | Links | |||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| CorDA2022.04 | 93.3 | 61.6 | 85.3 | 19.6 | 5.1 | 37.8 | 36.6 | 42.8 | 84.9 | 90.4 | 69.7 | 41.8 | 85.6 | 38.4 | 32.6 | 53.9 | 55 | — | — | — | — | — | — | — | — | |
| CorDABackbone=ResNet-101, Framework=DeepLab-v22024.03 | 93.3 | 61.6 | 85.3 | 19.6 | 5.1 | 37.8 | 36.6 | 42.8 | 84.9 | 90.4 | 69.7 | 41.8 | 85.6 | 38.4 | 32.6 | 53.9 | 55 | — | — | — | — | — | — | — | — | |
| CorDA (stereo)Depth=Used, Depth Estimation=Stereoscopic2021.04 | 93.3 | 61.6 | 85.3 | 19.6 | 510 | 37.8 | 36.6 | 42.8 | 84.9 | 90.4 | 69.7 | 41.8 | 85.6 | 38.4 | 32.6 | 53.9 | 55 | 62.8 | — | — | — | — | — | — | — | |
| UDACTimage translation=true, adversarial training=true, self-supervised learning=true2021.09 | 93.3 | 54 | 81.3 | 14.3 | 70 | 28.8 | 21.3 | 22.8 | 82.6 | 83.3 | 57.7 | 22.8 | 83.4 | 30.7 | 20.2 | 47.2 | 46.5 | 53.9 | — | — | — | — | — | — | — | |
| BiMaLNetwork=DL-V22023.04 | 92.8 | 51.5 | 81.5 | — | — | 30.4 | 17.6 | 100 | 82.4 | 84.6 | 55.9 | 22.3 | 85.7 | 38.8 | 24.6 | 10.2 | 46.2 | — | — | — | — | — | 15.9 | 44.5 | 30.9 | |
| LTIRBackbone=RN-101, Year=2020, Category=Image-to-Image / Style Transfer Methods2021.05 | 92.6 | 53.2 | 79.2 | — | — | 1.6 | 7.5 | 78.6 | 84.4 | 52.6 | 20 | 82.1 | 34.8 | 14.6 | 39.4 | — | — | — | — | 49.3 | — | — | — | — | — | |
| TIRimage translation=true, adversarial training=true, self-supervised learning=true2021.09 | 92.6 | 53.2 | 79.2 | — | — | — | 1.6 | 7.5 | 78.6 | 84.4 | 52.6 | 20 | 82.1 | 34.8 | 14.6 | 39.4 | — | 49.3 | — | — | — | — | — | — | — | |
| PixMatch (Fourier + CutMix)Backbone=RN-1012021.05 | 92.5 | 54.6 | 79.8 | 4.78 | 0.08 | 24.1 | 22.8 | 17.8 | 79.4 | 76.5 | 60.8 | 24.7 | 85.7 | 33.5 | 26.4 | 54.4 | — | — | 46.1 | 54.5 | — | — | — | — | — | |
| SEDA (Ours)adversarial training=true, self-supervised learning=true2021.09 | 92 | 53.9 | 82 | 10.1 | 20 | 32.8 | 13.3 | 26 | 83.6 | 84.4 | 63 | 21.4 | 86.7 | 46.8 | 24.7 | 49 | 48.1 | 55.9 | — | — | — | — | — | — | — | |
| BAPA2022.04 | 91.7 | 53.8 | 83.9 | 22.4 | 0.8 | 34.9 | 30.5 | 42.8 | 86.6 | 88.2 | 66 | 34.1 | 86.6 | 51.3 | 29.4 | 50.5 | 53.3 | — | — | — | — | — | — | — | — | |
| ATPSource-Free=true2026.03 | 90.6 | 54.4 | 86.7 | 28.5 | 0.5 | 50.3 | 52.4 | 50.5 | 87.4 | 93.4 | 70.2 | 35.8 | 89.6 | 53.5 | 50.6 | 51.1 | 59.1 | — | — | — | — | — | — | — | — | |
| TransDANetwork=Trans.2023.04 | 90.4 | 54.8 | 86.4 | — | — | 53.8 | 61.1 | 170 | 90.3 | 93 | 71.2 | 25.3 | 92.3 | 49.8 | 44.4 | 31.1 | 59.3 | — | — | — | — | — | 37.1 | 66 | 27.3 | |
| TransDA-BSource-Free=false2026.03 | 90.4 | 54.8 | 86.4 | 31.1 | 1.7 | 53.8 | 61.1 | 37.1 | 90.3 | 93 | 71.2 | 25.3 | 92.3 | 66 | 44.4 | 49.8 | 59.3 | — | — | — | — | — | — | — | — | |
| CorDA (mono)Depth=Used, Depth Estimation=Monocular (Monodepth2)2021.04 | 90.2 | 47.5 | 85.6 | 24.5 | 300 | 38.2 | 41.6 | 36.5 | 85.9 | 91.7 | 70.3 | 42.4 | 86 | 42.9 | 34.7 | 50.4 | 54.5 | 62 | — | — | — | — | — | — | — | |
| SSASource-Free=true2026.03 | 90 | 51.9 | 87 | 35.4 | 1 | 56.7 | 64.6 | 53.6 | 88.5 | 92.3 | 78.3 | 44.4 | 89.8 | 63.4 | 62.8 | 65.1 | 64.1 | — | — | — | — | — | — | — | — | |
| FREDOMNetwork=Trans.2023.04 | 89.4 | 50.8 | 89.3 | — | — | 57.3 | 65.1 | 930 | 89.9 | 93.7 | 79.4 | 51.6 | 90.5 | 68.1 | 62.3 | 48.8 | 67 | — | — | — | — | — | 60.1 | 66 | 22 | |
| SACNetwork=DL-V22023.04 | 89.3 | 47.3 | 85.6 | — | — | 43.1 | 45.6 | 130 | 87.1 | 89.1 | 63.7 | 25.3 | 87 | 52.8 | 30.3 | 26.6 | 52.6 | — | — | — | — | — | 32 | 35.6 | 27.9 | |
| SACBackbone=ResNet-101, Framework=DeepLab-v22024.03 | 89.3 | 47.2 | 85.5 | 26.5 | 1.3 | 43 | 45.5 | 32 | 87.1 | 89.3 | 63.6 | 25.4 | 86.9 | 35.6 | 30.4 | 53 | 52.6 | — | — | — | — | — | — | — | — | |
| DADADepth=Used2021.04 | 89.2 | 44.8 | 81.4 | 6.8 | 30 | 26.2 | 8.6 | 11.1 | 81.8 | 84 | 54.7 | 19.3 | 79.7 | 40.7 | 14 | 38.8 | 42.6 | 49.8 | — | — | — | — | — | — | — | |
| DACSBackbone=ResNet-101, Framework=DeepLab-v2, Guidance Training=true2024.03 | 88.8 | 50.4 | 85 | 14.1 | 2.6 | 36.9 | 44.4 | 44.2 | 88.2 | 88.4 | 69.9 | 45 | 86 | 48.9 | 39.2 | 61.6 | 55.6 | — | — | — | — | — | — | — | — | |
| FSTsetting=UDA, base_method=DAFormer2022.09 | 88.3 | 46.1 | 88 | 41.7 | 7.3 | 50.1 | 53.6 | 52.5 | 87.4 | 91.5 | 73.9 | 48.1 | 85.3 | 58.6 | 55.9 | 63.4 | 61.9 | — | — | — | — | — | — | — | — | |
| ProDA2022.04 | 87.8 | 45.7 | 84.6 | 37.1 | 0.6 | 44 | 54.6 | 37 | 88.1 | 84.4 | 74.2 | 24.3 | 88.2 | 51.1 | 40.5 | 45.6 | 55.5 | — | — | — | — | — | — | — | — | |
| ProDAsetting=UDA2022.09 | 87.8 | 45.7 | 84.6 | 37.1 | 0.6 | 44 | 54.6 | 37 | 88.1 | 84.4 | 74.2 | 24.3 | 88.2 | 51.1 | 40.5 | 45.6 | 55.5 | — | — | — | — | — | — | — | — | |
| ProDANetwork=DL-V22023.04 | 87.8 | 45.7 | 84.6 | — | — | 44 | 54.6 | 60 | 88.1 | 84.4 | 74.2 | 24.3 | 88.2 | 45.6 | 40.5 | 37.1 | 55.5 | — | — | — | — | — | 37 | 51.1 | 26.4 | |
| ProDABackbone=ResNet-101, Framework=DeepLab-v22024.03 | 87.8 | 45.7 | 84.6 | 37.1 | 0.6 | 44 | 54.6 | 37 | 88.1 | 84.4 | 74.2 | 24.3 | 88.2 | 51.1 | 40.5 | 45.6 | 55.5 | — | — | — | — | — | — | — | — | |
| MRNet + Oursmethodology=variance regularization2020.03 | 87.6 | 41.9 | 83.1 | 14.7 | 1.7 | 36.2 | 31.3 | 19.9 | 81.6 | 80.6 | 63 | 21.8 | 86.2 | 40.7 | 23.6 | 53.1 | 47.9 | 54.9 | — | — | — | — | — | — | — | |
| R-MRNetDepth=None2021.04 | 87.6 | 41.9 | 83.1 | 14.7 | 170 | 36.2 | 31.3 | 19.9 | 81.6 | 80.6 | 63 | 21.8 | 86.2 | 40.7 | 23.6 | 53.1 | 47.9 | 54.9 | — | — | — | — | — | — | — | |
| CPSLsetting=UDA2022.09 | 87.2 | 43.9 | 85.5 | 33.6 | 0.3 | 47.7 | 57.4 | 37.2 | 87.8 | 88.5 | 79 | 32 | 90.6 | 49.4 | 50.8 | 59.8 | 57.9 | — | — | — | — | — | — | — | — | |
| DASTadversarial training=true, self-supervised learning=true2021.09 | 87.1 | 44.5 | 82.3 | 10.7 | 80 | 29.9 | 13.9 | 13.1 | 81.6 | 86 | 60.3 | 25.1 | 83.1 | 40.1 | 24.4 | 40.5 | 45.2 | 52.5 | — | — | — | — | — | — | — | |
| AdvEntBackbone=RN-101, Year=2019, Category=Adversarial Methods2021.05 | 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 | — | — | 40.8 | 47.6 | — | — | — | — | — | |
| APODAArch.=AT2020.08 | 86.4 | 41.3 | 79.3 | — | — | — | 22.6 | 17.3 | 80.3 | 81.6 | 56.9 | 21 | 84.1 | 49.1 | 24.6 | 45.7 | 53.1 | — | — | — | — | — | — | — | — | |
| APODA2020.03 | 86.4 | 41.3 | 79.3 | — | — | — | 22.6 | 17.3 | 80.3 | 81.6 | 56.9 | 21 | 84.1 | 49.1 | 24.6 | 45.7 | — | 53.1 | — | — | — | — | — | — | — | |
| CTRLDepth=Used2021.04 | 86.4 | 42.5 | 80.4 | 20 | 100 | 27.7 | 10.5 | 13.3 | 80.6 | 82.6 | 61 | 23.7 | 81.8 | 42.9 | 21 | 44.7 | 45 | 51.5 | — | — | — | — | — | — | — | |
| DAF+IDABackbone=ResNet-101, Framework=DeepLab-v22024.03 | 86.3 | 41.6 | 81.4 | 18.3 | 1.3 | 25.1 | 11 | 10.5 | 82.9 | 85.6 | 62.4 | 27.1 | 83.9 | 55.9 | 33.3 | 41.2 | 46.7 | — | — | — | — | — | — | — | — | |
| CrCDA RBackbone=RN-101, Year=2020, Category=Adversarial Methods2021.05 | 86.2 | 44.9 | 79.5 | 8.3 | 0.7 | 27.8 | 9.4 | 11.8 | 78.6 | 86.5 | 57.2 | 26.1 | 76.8 | 39.9 | 21.5 | 32.1 | — | — | 42.9 | 50 | — | — | — | — | — | |
| BLFArch.=A&S2020.08 | 86 | 46.7 | 80.3 | — | — | — | 14.1 | 11.6 | 79.2 | 81.3 | 54.1 | 27.9 | 73.7 | 42.2 | 25.7 | 45.3 | 51.4 | — | — | — | — | — | — | — | — | |
| BDL2021.03 | 86 | 46.7 | 80.3 | — | — | — | 14.1 | 11.6 | 79.2 | 81.3 | 54.1 | 27.9 | 73.7 | 42.2 | 25.7 | 45.3 | — | 51.4 | — | — | — | — | — | — | — | |
| BDL (M2-F2)Backbone=RN-101, Year=2019, Category=Image-to-Image / Style Transfer Methods2021.05 | 86 | 46.7 | 80.3 | — | — | 14.1 | 11.6 | 79.2 | 81.3 | 54.1 | 27.9 | 73.7 | 42.2 | 25.7 | 45.3 | — | — | — | — | 51.4 | — | — | — | — | — | |
| FREDOMNetwork=DL-V22023.04 | 86 | 46.3 | 87 | — | — | 48.7 | 53.4 | 530 | 87.1 | 89.1 | 71.2 | 38.1 | 87.1 | 59.9 | 51.3 | 33.3 | 59.1 | — | — | — | — | — | 46.8 | 54.6 | 24 | |
| BDLimage translation=true, adversarial training=true, self-supervised learning=true2021.09 | 86 | 46.7 | 80.3 | — | — | — | 14.1 | 11.6 | 79.2 | 81.3 | 54.1 | 27.9 | 73.7 | 42.2 | 25.7 | 45.3 | — | 51.4 | — | — | — | — | — | — | — | |
| HRDABackbone=ResNet-101, Framework=DeepLab-v2, Guidance Training=false2024.03 | 85.8 | 47.3 | 87.3 | 27.3 | 1.4 | 50.5 | 57.8 | 61 | 87.4 | 89.1 | 76.2 | 48.5 | 87.3 | 49.3 | 55 | 68.2 | 61.2 | — | — | — | — | — | — | — | — | |
| AdvEntArch.=AT2020.08 | 85.6 | 42.2 | 79.7 | 8.7 | 0.4 | 25.9 | 5.4 | 8.1 | 80.4 | 84.1 | 57.9 | 23.8 | 73.3 | 36.4 | 14.2 | 33 | 41.2 | 48 | — | — | — | — | — | — | — | |
| AdvEnt2020.03 | 85.6 | 42.2 | 79.7 | 8.7 | 0.4 | 25.9 | 5.4 | 8.1 | 80.4 | 84.1 | 57.9 | 23.8 | 73.3 | 36.4 | 14.2 | 33 | 41.2 | 48 | — | — | — | — | — | — | — | |
| AdvEnt+MinEntBackbone=RN-101, Year=2019, Category=Adversarial Methods2021.05 | 85.6 | 42.2 | 79.7 | 8.7 | 0.4 | 25.9 | 5.4 | 8.1 | 80.4 | 84.1 | 57.9 | 23.8 | 73.3 | 36.4 | 14.2 | 33 | — | — | 41.2 | 48 | — | — | — | — | — | |
| ADVENTDepth=None2021.04 | 85.6 | 42.2 | 79.7 | 8.7 | 40 | 25.9 | 5.4 | 8.1 | 80.4 | 84.1 | 57.9 | 23.8 | 73.3 | 36.4 | 14.2 | 33 | 41.2 | 48 | — | — | — | — | — | — | — | |
| ADVENTadversarial training=true2021.09 | 85.6 | 42.2 | 79.7 | 8.7 | 40 | 25.9 | 5.4 | 8.1 | 80.4 | 84.1 | 57.9 | 23.8 | 73.3 | 36.4 | 14.2 | 33 | 41.2 | 48 | — | — | — | — | — | — | — | |
| HRDA2022.04 | 85.2 | 47.7 | 88.8 | 49.5 | 4.8 | 57.2 | 65.7 | 60.9 | 85.3 | 92.9 | 79.4 | 52.8 | 89 | 64.7 | 63.9 | 64.9 | 65.8 | — | — | — | — | — | — | — | — | |
| HRDASource-Free=false2026.03 | 85.2 | 47.7 | 88.8 | 49.5 | 4.8 | 57.2 | 65.7 | 60.9 | 85.3 | 92.9 | 79.4 | 52.8 | 89 | 64.7 | 63.9 | 64.9 | 65.8 | — | — | — | — | — | — | — | — | |
| Yang et al.Depth=None2021.04 | 85.1 | 44.5 | 81 | — | — | — | 16.4 | 15.2 | 80.1 | 84.8 | 59.4 | 31.9 | 73.2 | 41 | 32.6 | 44.7 | — | 53.1 | — | — | — | — | — | — | — | |
| LDRimage translation=true, adversarial training=true, self-supervised learning=true2021.09 | 85.1 | 44.5 | 81 | — | — | — | 16.4 | 15.2 | 80.1 | 84.8 | 59.4 | 31.9 | 73.2 | 41 | 32.6 | 44.7 | — | 53.1 | — | — | — | — | — | — | — | |
| CAGevaluation_classes=132021.03 | 84.8 | 41.7 | 85.5 | — | — | — | 13.7 | 23 | 86.5 | 78.1 | 66.3 | 28.1 | 81.8 | 21.8 | 22.9 | 49 | — | 52.6 | — | — | — | — | — | — | — | |
| PixMatch (CutMix)Backbone=RN-1012021.05 | 84.8 | 42.1 | 81 | 6.98 | 0.25 | 27.9 | 15.6 | 16.6 | 82.3 | 80.7 | 53.9 | 21.8 | 83.1 | 39.3 | 21 | 43.1 | — | — | 43.8 | 51.2 | — | — | — | — | — | |
| CAGevaluation_classes=162021.03 | 84.7 | 40.8 | 81.7 | 7.8 | 0 | 35.1 | 13.3 | 22.7 | 84.5 | 77.6 | 64.2 | 27.8 | 80.9 | 19.7 | 22.7 | 48.3 | 44.5 | — | — | — | — | — | — | — | — | |
| CAGBackbone=RN-101, Year=2019, Category=Adversarial Methods2021.05 | 84.7 | 40.8 | 81.7 | 7.8 | 0 | 35.1 | 13.3 | 22.7 | 84.5 | 77.6 | 64.2 | 27.8 | 80.9 | 19.7 | 22.7 | 48.3 | — | — | 44.5 | 52.6 | — | — | — | — | — | |
| MICBackbone=ResNet-101, Framework=DeepLab-v2, Guidance Training=false2024.03 | 84.7 | 45.7 | 88.3 | 29.9 | 2.8 | 53.3 | 61 | 59.5 | 86.9 | 88.8 | 78.2 | 53.3 | 89.4 | 58.8 | 56 | 68.3 | 62.8 | — | — | — | — | — | — | — | — | |
| MICBackbone=ResNet-101, Framework=DeepLab-v2, Guidance Training=true2024.03 | 84.7 | 45.3 | 88 | 37.3 | 2.8 | 53.3 | 62.5 | 61.8 | 87.2 | 88.5 | 78.3 | 53.7 | 90.4 | 60.9 | 56.1 | 71.4 | 63.8 | — | — | — | — | — | — | — | — | |
| SSF-DANArch.=AT2020.08 | 84.6 | 41.7 | 80.8 | — | — | — | 11.5 | 14.7 | 80.8 | 85.3 | 57.5 | 21.6 | 82 | 36 | 19.3 | 34.5 | 50 | — | — | — | — | — | — | — | — | |
| FGGAN2021.03 | 84.5 | 40.1 | 83.1 | 4.8 | 0 | 34.3 | 20.1 | 27.2 | 84.8 | 84 | 53.5 | 22.6 | 85.4 | 43.7 | 26.8 | 27.8 | 45.2 | 52.5 | — | — | — | — | — | — | — | |
| FADABackbone=RN-101, Year=2020, Category=Adversarial Methods2021.05 | 84.5 | 40.1 | 83.1 | 4.8 | 0 | 34.3 | 20.1 | 27.2 | 84.8 | 84 | 53.5 | 22.6 | 85.4 | 43.7 | 26.8 | 27.8 | — | — | 45.2 | 52.5 | — | — | — | — | — | |
| DAFormer2022.04 | 84.5 | 40.7 | 88.4 | 41.5 | 6.5 | 50 | 55 | 54.6 | 86 | 89.8 | 73.2 | 48.2 | 87.2 | 53.2 | 53.9 | 61.7 | 60.9 | — | — | — | — | — | — | — | — | |
| DAFormersetting=UDA2022.09 | 84.5 | 40.7 | 88.4 | 41.5 | 6.5 | 50 | 55 | 54.6 | 86 | 89.8 | 73.2 | 48.2 | 87.2 | 53.2 | 53.9 | 61.7 | 60.9 | — | — | — | — | — | — | — | — | |
| DAFormerNetwork=Trans.2023.04 | 84.5 | 40.7 | 88.4 | — | — | 50 | 55 | 650 | 86 | 89.8 | 73.2 | 48.2 | 87.2 | 61.7 | 53.9 | 41.5 | 60.9 | — | — | — | — | — | 54.6 | 53.2 | 22.8 | |
| HRDABackbone=ResNet-101, Framework=DeepLab-v2, Guidance Training=true2024.03 | 84.5 | 45.5 | 87 | 28.7 | 2.7 | 50.8 | 61 | 62.6 | 87.7 | 88.5 | 78.8 | 53.5 | 89.1 | 58.4 | 57.2 | 68.8 | 62.8 | — | — | — | — | — | — | — | — | |
| FADAadversarial training=true, self-supervised learning=true2021.09 | 84.5 | 40.1 | 83.1 | 4.8 | 0 | 34.3 | 20.1 | 27.2 | 84.8 | 84 | 53.5 | 22.6 | 85.4 | 43.7 | 26.8 | 27.8 | 45.2 | 52.5 | — | — | — | — | — | — | — | |
| DAFormerSource-Free=false2026.03 | 84.5 | 40.7 | 88.4 | 41.5 | 6.5 | 50 | 55 | 54.6 | 86 | 89.8 | 73.2 | 48.2 | 87.2 | 53.2 | 53.9 | 61.7 | 60.9 | — | — | — | — | — | — | — | — | |
| AdaptSegNetArch.=AT2020.08 | 84.3 | 42.7 | 77.5 | — | — | — | 4.7 | 7 | 77.9 | 82.5 | 54.3 | 21 | 72.3 | 32.2 | 18.9 | 32.3 | 46.7 | — | — | — | — | — | — | — | — | |
| AdaptSegNet2020.03 | 84.3 | 42.7 | 77.5 | — | — | — | 4.7 | 7 | 77.9 | 82.5 | 54.3 | 21 | 72.3 | 32.2 | 18.9 | 32.3 | — | 46.7 | — | — | — | — | — | — | — | |
| IDA2021.03 | 84.3 | 37.7 | 79.5 | 5.3 | 0.4 | 24.9 | 9.2 | 8.4 | 80 | 84.1 | 57.2 | 23 | 78 | 38.1 | 20.3 | 36.5 | 41.7 | 48.9 | — | — | — | — | — | — | — | |
| IntraDABackbone=RN-101, Year=2020, Category=Other Methods2021.05 | 84.3 | 37.7 | 79.5 | 5.3 | 0.4 | 24.9 | 9.2 | 8.4 | 80 | 84.1 | 57.2 | 23 | 78 | 38.1 | 20.3 | 36.5 | — | — | 41.7 | 48.9 | — | — | — | — | — | |
| IntraDANetwork=DL-V22023.04 | 84.3 | 37.7 | 79.5 | — | — | 24.9 | 9.2 | 40 | 80 | 84.1 | 57.2 | 23 | 78 | 36.5 | 20.3 | 5.3 | 41.7 | — | — | — | — | — | 8.4 | 38.1 | 31 | |
| ProCSTNetwork=Trans.2023.04 | 84.3 | 41.1 | 87.7 | — | — | 50.7 | 55.5 | 610 | 86.1 | 87.9 | 74.7 | 47.2 | 87.6 | 62.5 | 53.3 | 42.6 | 61.4 | — | — | — | — | — | 54.2 | 61.4 | 22.6 | |
| OutputAdaptDepth=None2021.04 | 84.3 | 42.7 | 77.5 | — | — | — | 4.7 | 7 | 77.9 | 82.5 | 54.3 | 21 | 72.3 | 32.2 | 18.9 | 32.3 | — | 46.7 | — | — | — | — | — | — | — | |
| IntraDAadversarial training=true, self-supervised learning=true2021.09 | 84.3 | 37.7 | 79.5 | 5.3 | 40 | 24.9 | 9.2 | 8.4 | 80 | 84.1 | 57.2 | 23 | 78 | 38.1 | 20.3 | 36.5 | 41.7 | 48.9 | — | — | — | — | — | — | — | |
| AdaptSegNet-LSBackbone=RN-101, Year=2018, Category=Adversarial Methods2021.05 | 84 | 40.5 | 79.3 | 10.4 | 0.2 | 22.7 | 6.5 | 8 | 78.3 | 82.7 | 56.3 | 22.4 | 74 | 33.2 | 18.9 | 34.9 | — | — | 40.8 | 47.6 | — | — | — | — | — | |
| AdaptMRArch.=A&S2020.08 | 83.1 | 38.2 | 81.7 | 9.3 | 1 | 35.1 | 30.3 | 19.9 | 82 | 80.1 | 62.8 | 21.1 | 84.4 | 37.8 | 24.5 | 53.3 | 46.5 | 53.8 | — | — | — | — | — | — | — | |
| MRNet + Pseudo2020.03 | 83.1 | 38.2 | 81.7 | 9.3 | 1 | 35.1 | 30.3 | 19.9 | 82 | 80.1 | 62.8 | 21.1 | 84.4 | 37.8 | 24.5 | 53.3 | 46.5 | 53.8 | — | — | — | — | — | — | — | |
| DTST2021.03 | 83 | 44 | 80.3 | — | — | — | 17.1 | 15.8 | 80.5 | 81.8 | 59.9 | 33.1 | 70.2 | 37.3 | 28.5 | 45.8 | — | 52.1 | — | — | — | — | — | — | — | |
| SIMDepth=None2021.04 | 83 | 44 | 80.3 | — | — | — | 17.1 | 15.8 | 80.5 | 81.8 | 59.9 | 33.1 | 70.2 | 37.3 | 28.5 | 45.8 | — | 48.3 | — | — | — | — | — | — | — | |
| MS + IW + MultiBackbone=RN-101, Year=2019, Category=Self-Training Methods2021.05 | 82.9 | 40.7 | 80.3 | 10.2 | 0.8 | 25.8 | 12.8 | 18.2 | 82.5 | 82.2 | 53.1 | 18 | 79 | 31.4 | 10.4 | 35.6 | — | — | 41.4 | 48.2 | — | — | — | — | — | |
| PixMatch (Fourier)Backbone=RN-1012021.05 | 82.9 | 36.2 | 81.7 | 9.74 | 0.11 | 29.7 | 16.7 | 19.2 | 84.3 | 84.2 | 62.3 | 16.9 | 84.6 | 39.4 | 3.04 | 52.5 | — | — | 44 | 51.1 | — | — | — | — | — | |
| PLCABackbone=RN-101, Year=2020, Category=Other Methods2021.05 | 82.6 | 29 | 81 | 11.2 | 0.2 | 33.6 | 24.9 | 18.3 | 82.8 | 82.3 | 62.1 | 26.5 | 85.6 | 48.9 | 26.8 | 52.2 | — | — | 46.8 | 54 | — | — | — | — | — | |
| SIBANArch.=AT2020.08 | 82.5 | 24 | 79.4 | — | — | — | 16.5 | 12.7 | 79.2 | 82.8 | 58.3 | 18 | 79.3 | 25.3 | 17.6 | 25.9 | 46.3 | — | — | — | — | — | — | — | — | |
| SIBAN2020.03 | 82.5 | 24 | 79.4 | — | — | — | 16.5 | 12.7 | 79.2 | 82.8 | 58.3 | 18 | 79.3 | 25.3 | 17.6 | 25.9 | — | 46.3 | — | — | — | — | — | — | — | |
| patch-level alignmentBackbone=ResNet-1012019.01 | 82.4 | 38 | 78.6 | 8.7 | 0.6 | 26 | 3.9 | 11.1 | 75.5 | 84.6 | 53.5 | 21.6 | 71.4 | 32.6 | 19.3 | 31.7 | 40 | 46.5 | — | — | — | — | — | — | — | |
| PatchAlignArch.=A&S2020.08 | 82.4 | 38 | 78.6 | 8.7 | 0.6 | 26 | 3.9 | 11.1 | 75.5 | 84.6 | 53.5 | 21.6 | 71.4 | 32.6 | 19.3 | 31.7 | 40 | 46.5 | — | — | — | — | — | — | — | |
| PatchAlign2020.03 | 82.4 | 38 | 78.6 | 8.7 | 0.6 | 26 | 3.9 | 11.1 | 75.5 | 84.6 | 53.5 | 21.6 | 71.4 | 32.6 | 19.3 | 31.7 | 40 | 46.5 | — | — | — | — | — | — | — | |
| Patch-DiscBackbone=RN-101, Year=2019, Category=Adversarial Methods2021.05 | 82.4 | 38 | 78.6 | 8.7 | 0.6 | 26 | 3.9 | 11.1 | 75.5 | 84.6 | 53.5 | 21.6 | 71.4 | 32.6 | 19.3 | 31.7 | — | — | 40 | 46.5 | — | — | — | — | — | |
| SWDBackbone=RN-101, Year=2019, Category=Other Methods2021.05 | 82.4 | 33.2 | 82.5 | — | — | 22.6 | 19.7 | 83.7 | 78.8 | 44 | 17.9 | 75.4 | 30.2 | 14.4 | 39.9 | — | — | — | — | 48.1 | — | — | — | — | — | |
| AdaptPatchadversarial training=true2021.09 | 82.4 | 38 | 78.6 | 8.7 | 60 | 26 | 3.9 | 11.1 | 75.5 | 84.6 | 53.5 | 21.6 | 71.4 | 32.6 | 19.3 | 31.7 | 40 | 46.5 | — | — | — | — | — | — | — | |
| IDMSource-Free=true2026.03 | 82.2 | 37.9 | 83.5 | 20.3 | 1.5 | 47.3 | 41.7 | 25.6 | 84.4 | 86.8 | 61.6 | 25 | 87.6 | 43.7 | 30.2 | 36.4 | 49.7 | — | — | — | — | — | — | — | — | |
| PixMatch (Style)Backbone=RN-1012021.05 | 82.1 | 38 | 76.2 | 3.97 | 0.12 | 26.4 | 14.2 | 11 | 75.5 | 70.7 | 54.3 | 20.6 | 75.8 | 36.9 | 19.4 | 39.3 | — | — | 40.3 | 47.3 | — | — | — | — | — | |
| MRNet2020.03 | 82 | 36.5 | 80.4 | 4.2 | 0.4 | 33.7 | 18 | 13.4 | 81.1 | 80.8 | 61.3 | 21.7 | 84.4 | 32.4 | 14.8 | 45.7 | 43.2 | 50.2 | — | — | — | — | — | — | — | |
| IAST(ours)Arch.=A&S2020.08 | 81.9 | 41.5 | 83.3 | 17.7 | 4.6 | 32.3 | 30.9 | 28.8 | 83.4 | 85 | 65.5 | 30.8 | 86.5 | 38.2 | 33.1 | 52.7 | 49.8 | 57 | — | — | — | — | — | — | — | |
| IASTBackbone=ResNet-101, Framework=DeepLab-v22024.03 | 81.9 | 41.5 | 83.3 | 17.7 | 4.6 | 32.3 | 30.9 | 28.8 | 83.4 | 85 | 65.5 | 30.8 | 86.5 | 38.2 | 33.1 | 52.7 | 49.8 | — | — | — | — | — | — | — | — | |
| IASTDepth=None2021.04 | 81.9 | 41.5 | 83.3 | 17.7 | 460 | 32.3 | 30.9 | 28.8 | 83.4 | 85 | 65.5 | 30.8 | 86.5 | 38.2 | 33.1 | 52.7 | 49.8 | 57 | — | — | — | — | — | — | — | |
| AdaSegNetadversarial training=true2021.09 | 81.7 | 39.1 | 78.4 | 11.1 | 30 | 25.8 | 6.8 | 9 | 79.1 | 80.8 | 54.8 | 21 | 66.8 | 34.7 | 13.8 | 29.9 | 39.6 | 45.8 | — | — | — | — | — | — | — | |
| CLAN2020.03 | 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 | — | — | — | — | — | — | — | |
| CLANadversarial training=true2021.09 | 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 | — | — | — | — | — | — | — | |
| DACS2022.04 | 80.6 | 25.1 | 81.9 | 21.5 | 2.9 | 37.2 | 22.7 | 24 | 83.7 | 90.8 | 67.6 | 38.3 | 82.9 | 38.9 | 28.5 | 47.6 | 48.3 | — | — | — | — | — | — | — | — | |
| DACSBackbone=ResNet-101, Framework=DeepLab-v2, Guidance Training=false2024.03 | 80.6 | 25.1 | 81.9 | 21.5 | 2.9 | 37.2 | 22.7 | 24 | 83.7 | 90.8 | 67.6 | 38.3 | 82.9 | 38.9 | 28.5 | 47.6 | 48.3 | — | — | — | — | — | — | — | — |