Semantic Segmentation on Cityscapes 1.0 (val)
80.21mIoUCPS+CutMix
Evaluation results
| Method | Links | ||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| CPS+CutMixBackbone=ResNet-101, Supervision ratio=1/2, Segmentation framework=DeepLabv3+2021.12 | 80.21 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CPSBackbone=ResNet-101, Supervision ratio=1/2, Segmentation framework=DeepLabv3+2021.12 | 80.08 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| 3-CPS-mcBackbone=ResNet-50, Supervision ratio=1/2, Segmentation framework=DeepLabv3+2021.12 | 79.29 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| 3-CPS-svBackbone=ResNet-50, Supervision ratio=1/2, Segmentation framework=DeepLabv3+2021.12 | 79.27 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CPS+CutMixBackbone=ResNet-101, Supervision ratio=1/4, Segmentation framework=DeepLabv3+2021.12 | 79.21 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| 3-CPS-sv+CutMixBackbone=ResNet-50, Supervision ratio=1/2, Segmentation framework=DeepLabv3+2021.12 | 79.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| 3-CPS-mc+CutMixBackbone=ResNet-50, Supervision ratio=1/2, Segmentation framework=DeepLabv3+2021.12 | 79.15 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CPS+CutMixBackbone=ResNet-50, Supervision ratio=1/2, Segmentation framework=DeepLabv3+2021.12 | 78.77 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CPSBackbone=ResNet-50, Supervision ratio=1/2, Segmentation framework=DeepLabv3+2021.12 | 78.64 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MTBackbone=ResNet-101, Supervision ratio=1/2, Segmentation framework=DeepLabv3+2021.12 | 78.59 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| GCTBackbone=ResNet-101, Supervision ratio=1/2, Segmentation framework=DeepLabv3+2021.12 | 78.58 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| 3-CPS-sv+CutMixBackbone=ResNet-50, Supervision ratio=1/4, Segmentation framework=DeepLabv3+2021.12 | 78.41 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| 3-CPS-mc+CutMixBackbone=ResNet-50, Supervision ratio=1/4, Segmentation framework=DeepLabv3+2021.12 | 78.36 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CCTBackbone=ResNet-101, Supervision ratio=1/2, Segmentation framework=DeepLabv3+2021.12 | 78.29 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CPS+CutMixBackbone=ResNet-50, Supervision ratio=1/4, Segmentation framework=DeepLabv3+2021.12 | 77.83 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CPS+CutMixBackbone=ResNet-101, Supervision ratio=1/8, Segmentation framework=DeepLabv3+2021.12 | 77.62 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| 3-CPS-sv+CutMixBackbone=ResNet-50, Supervision ratio=1/8, Segmentation framework=DeepLabv3+2021.12 | 77.61 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| 3-CPS-mc+CutMixBackbone=ResNet-50, Supervision ratio=1/8, Segmentation framework=DeepLabv3+2021.12 | 77.58 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MTBackbone=ResNet-50, Supervision ratio=1/2, Segmentation framework=DeepLabv3+2021.12 | 77.43 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CPSBackbone=ResNet-101, Supervision ratio=1/4, Segmentation framework=DeepLabv3+2021.12 | 77.41 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| GCTBackbone=ResNet-50, Supervision ratio=1/2, Segmentation framework=DeepLabv3+2021.12 | 77.09 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CPSBackbone=ResNet-50, Supervision ratio=1/4, Segmentation framework=DeepLabv3+2021.12 | 76.85 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CCTBackbone=ResNet-50, Supervision ratio=1/2, Segmentation framework=DeepLabv3+2021.12 | 76.78 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| 3-CPS-mcBackbone=ResNet-50, Supervision ratio=1/4, Segmentation framework=DeepLabv3+2021.12 | 76.74 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| 3-CPS-svBackbone=ResNet-50, Supervision ratio=1/4, Segmentation framework=DeepLabv3+2021.12 | 76.74 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CPS+CutMixBackbone=ResNet-50, Supervision ratio=1/8, Segmentation framework=DeepLabv3+2021.12 | 76.61 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MTBackbone=ResNet-101, Supervision ratio=1/4, Segmentation framework=DeepLabv3+2021.12 | 76.53 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| GCTBackbone=ResNet-101, Supervision ratio=1/4, Segmentation framework=DeepLabv3+2021.12 | 76.45 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CCTBackbone=ResNet-101, Supervision ratio=1/4, Segmentation framework=DeepLabv3+2021.12 | 76.35 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| 3-CPS-sv+CutMixBackbone=ResNet-50, Supervision ratio=1/16, Segmentation framework=DeepLabv3+2021.12 | 76.08 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| 3-CPS-mc+CutMixBackbone=ResNet-50, Supervision ratio=1/16, Segmentation framework=DeepLabv3+2021.12 | 76.06 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CPSBackbone=ResNet-101, Supervision ratio=1/8, Segmentation framework=DeepLabv3+2021.12 | 75.71 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CCTBackbone=ResNet-50, Supervision ratio=1/4, Segmentation framework=DeepLabv3+2021.12 | 75.68 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| SwiftNetRN-18+GPU=GTX 1080Ti, resolution=2048x1024, # params=11.8M, ImageNet pre-training=true2019.03 | 75.4 | 39.9 | 39.3 | 104 | 52 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| SwiftNetMN V2+GPU=GTX 1080Ti, resolution=2048x1024, # params=2.4M, ImageNet pre-training=true2019.03 | 75.3 | 27.7 | 27.7 | 41 | 20.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| GCTBackbone=ResNet-50, Supervision ratio=1/4, Segmentation framework=DeepLabv3+2021.12 | 75.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| 3-CPS-svBackbone=ResNet-50, Supervision ratio=1/8, Segmentation framework=DeepLabv3+2021.12 | 74.88 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| 3-CPS-mcBackbone=ResNet-50, Supervision ratio=1/8, Segmentation framework=DeepLabv3+2021.12 | 74.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CPS+CutMixBackbone=ResNet-101, Supervision ratio=1/16, Segmentation framework=DeepLabv3+2021.12 | 74.72 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CCTBackbone=ResNet-101, Supervision ratio=1/8, Segmentation framework=DeepLabv3+2021.12 | 74.48 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MTBackbone=ResNet-50, Supervision ratio=1/4, Segmentation framework=DeepLabv3+2021.12 | 74.47 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CPS+CutMixBackbone=ResNet-50, Supervision ratio=1/16, Segmentation framework=DeepLabv3+2021.12 | 74.47 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| SwiftNetRN-18 pyr+GPU=GTX 1080Ti, resolution=2048x1024, # params=12.9M, ImageNet pre-training=true, model_type=pyramid fusion2019.03 | 74.4 | 34 | 34 | 114 | 57 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CPSBackbone=ResNet-50, Supervision ratio=1/8, Segmentation framework=DeepLabv3+2021.12 | 74.39 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MTBackbone=ResNet-101, Supervision ratio=1/8, Segmentation framework=DeepLabv3+2021.12 | 73.71 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| GCTBackbone=ResNet-101, Supervision ratio=1/8, Segmentation framework=DeepLabv3+2021.12 | 72.96 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Ladder DenseNet+GPU=TitanX, resolution=1024x512, # params=9.8M2019.03 | 72.8 | 31 | 30.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CCTBackbone=ResNet-50, Supervision ratio=1/8, Segmentation framework=DeepLabv3+2021.12 | 72.46 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MTBackbone=ResNet-50, Supervision ratio=1/8, Segmentation framework=DeepLabv3+2021.12 | 72.03 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| GCTBackbone=ResNet-50, Supervision ratio=1/8, Segmentation framework=DeepLabv3+2021.12 | 71.33 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| DG2sGPU=TitanX M, resolution=1024x512, # params=1.2M2019.03 | 70.6 | — | — | 19 | 38 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CPSBackbone=ResNet-101, Supervision ratio=1/16, Segmentation framework=DeepLabv3+2021.12 | 70.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| SwiftNetRN-18GPU=GTX 1080Ti, resolution=2048x1024, # params=11.8M, ImageNet pre-training=false2019.03 | 70.4 | 39.9 | 39.3 | 104 | 52 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| SwiftNetRN-18+GPU=GTX 1080Ti, resolution=1024x512, # params=11.8M, ImageNet pre-training=true2019.03 | 70.2 | 134.9 | 134.9 | 26 | 52 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CPSBackbone=ResNet-50, Supervision ratio=1/16, Segmentation framework=DeepLabv3+2021.12 | 69.79 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| 3-CPS-mcBackbone=ResNet-50, Supervision ratio=1/16, Segmentation framework=DeepLabv3+2021.12 | 69.78 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| 3-CPS-svBackbone=ResNet-50, Supervision ratio=1/16, Segmentation framework=DeepLabv3+2021.12 | 69.76 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CCTBackbone=ResNet-101, Supervision ratio=1/16, Segmentation framework=DeepLabv3+2021.12 | 69.64 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| SwiftNetMN V2GPU=GTX 1080Ti, resolution=2048x1024, # params=2.4M, ImageNet pre-training=false2019.03 | 69.4 | 27.7 | 27.7 | 41 | 20.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| D*GPU=TitanX M, resolution=1024x512, # params=0.5M2019.03 | 68.4 | — | — | 5.8 | 11.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MTBackbone=ResNet-101, Supervision ratio=1/16, Segmentation framework=DeepLabv3+2021.12 | 68.08 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| GCTBackbone=ResNet-101, Supervision ratio=1/16, Segmentation framework=DeepLabv3+2021.12 | 66.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CCTBackbone=ResNet-50, Supervision ratio=1/16, Segmentation framework=DeepLabv3+2021.12 | 66.35 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MTBackbone=ResNet-50, Supervision ratio=1/16, Segmentation framework=DeepLabv3+2021.12 | 66.14 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| GCTBackbone=ResNet-50, Supervision ratio=1/16, Segmentation framework=DeepLabv3+2021.12 | 65.81 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| FCNStandard=Oracle, Backbone=VGG-162019.10 | 62.6 | — | — | — | — | 96.4 | 74.5 | 87.1 | 35.3 | 37.8 | 36.4 | 46.9 | 60.1 | 89 | 89.8 | 65.6 | 35.9 | 76.9 | 64.1 | 40.5 | 65.1 | — | — | — | |
| CMFormerSource Dataset=GTA52023.07 | 55.31 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Ensemble Self-Supervised Learning for UDATraining Stage=S2, SSL Round=R2, Classifier=Cm2021.07 | 51.66 | — | — | — | — | 92.59 | 53.05 | 86.31 | 34.2 | 27.17 | 39.13 | 41 | 44.8 | 86.1 | 84.69 | 67.23 | 29.77 | 85.78 | 29.9 | 35.55 | 57.05 | 34.32 | 32.73 | 20.12 | |
| Ensemble Self-Supervised Learning for UDATraining Stage=S2, SSL Round=R2, Classifier=C22021.07 | 51.29 | — | — | — | — | 92.27 | 51.59 | 86.19 | 35.28 | 26.84 | 36.73 | 35.68 | 42.4 | 86.84 | 85.49 | 66.9 | 27.6 | 85.75 | 32.85 | 33.89 | 58.1 | 37.3 | 32.26 | 20.59 | |
| PCEDA2021.07 | 50.5 | — | — | — | — | 91 | 49.2 | 85.6 | 37.2 | 29.7 | 33.7 | 38.1 | 39.2 | 85.4 | 85.1 | 61.1 | 32.8 | 84.1 | 46.9 | 34.2 | 44.5 | 35.4 | 45.6 | 0 | |
| FDA-MBT2021.07 | 50.45 | — | — | — | — | 92.5 | 53.3 | 82.4 | 26.5 | 27.6 | 36.4 | 40.6 | 38.9 | 82.3 | 78 | 62.6 | 34.4 | 84.9 | 53.1 | 27.7 | 46.4 | 39.8 | 34.1 | 16.9 | |
| Ensemble Self-Supervised Learning for UDATraining Stage=S2, SSL Round=R1, Classifier=Cm2021.07 | 49.5 | — | — | — | — | 90.81 | 47.85 | 85.01 | 32.08 | 24.55 | 37.73 | 38.15 | 42.13 | 85.37 | 84.97 | 66.51 | 28 | 84.51 | 25.14 | 35.03 | 56.02 | 34.32 | 27 | 15.23 | |
| Ensemble Self-Supervised Learning for UDATraining Stage=S2, SSL Round=R1, Classifier=C32021.07 | 48.94 | — | — | — | — | 90.6 | 46.94 | 84.06 | 31.9 | 23.88 | 37.53 | 34.81 | 34.37 | 85.69 | 84.32 | 66.53 | 29.41 | 85.46 | 32.48 | 36.05 | 54.96 | 36.02 | 27.77 | 7.15 | |
| BDL2021.07 | 48.5 | — | — | — | — | 91 | 44.7 | 84.2 | 34.6 | 27.6 | 30.2 | 36 | 36 | 85 | 83 | 58.6 | 31.6 | 83.3 | 49.7 | 28.8 | 35.6 | 43.6 | 35.3 | 3.3 | |
| ADVENT2021.07 | 45.5 | — | — | — | — | 89.4 | 33.1 | 81 | 26.6 | 26.8 | 27.2 | 33.5 | 24.7 | 83.9 | 78.8 | 58.7 | 30.5 | 84.8 | 44.5 | 31.6 | 32.4 | 36.7 | 38.5 | 1.7 | |
| ABStruct2021.07 | 45.4 | — | — | — | — | 91.5 | 47.5 | 82.5 | 31.3 | 25.6 | 33 | 33.7 | 25.8 | 82.7 | 82.7 | 62.4 | 30.8 | 85.2 | 34.5 | 25.2 | 24.4 | 28.8 | 27.7 | 6.4 | |
| Ensemble Self-Supervised Learning for UDATraining Stage=S1, Classifier=Cm2021.07 | 45.24 | — | — | — | — | 85.29 | 35.57 | 81.69 | 29.93 | 20.24 | 35.53 | 36.63 | 35.94 | 83.24 | 81.75 | 63.75 | 29.18 | 81.8 | 24.58 | 31 | 47.26 | 28.1 | 23.44 | 4.67 | |
| SHADESource Dataset=GTA5, Backbone=ResNet-502023.07 | 44.65 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| WildNetSource Dataset=GTA5, Backbone=ResNet-502023.07 | 44.62 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| SPCSource Dataset=GTA5, Backbone=ResNet-502023.07 | 44.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Ensemble Self-Supervised Learning for UDATraining Stage=S1, Classifier=C32021.07 | 43.32 | — | — | — | — | 87.22 | 36.57 | 81.26 | 28.65 | 17.82 | 35.55 | 32.58 | 29.11 | 83.46 | 77.06 | 62.48 | 28.78 | 81.49 | 22.85 | 29.85 | 35.14 | 30.39 | 22.75 | 0.06 | |
| CLAN2021.07 | 43.2 | — | — | — | — | 87 | 27.1 | 79.6 | 27.3 | 23.3 | 28.3 | 35.5 | 24.2 | 83.6 | 74.2 | 58.6 | 28 | 76.2 | 36.7 | 31.9 | 31.4 | 27.4 | 33.1 | 6.7 | |
| DLOW2021.07 | 42.3 | — | — | — | — | 87.1 | 33.5 | 80.5 | 24.5 | 13.2 | 29.8 | 29.5 | 26.6 | 82.6 | 81.8 | 55.9 | 25.3 | 78 | 38.7 | 22.9 | 34.5 | 26.7 | 33.5 | 0 | |
| DCAN2021.07 | 41.7 | — | — | — | — | 85 | 30.8 | 81.3 | 25.8 | 21.2 | 22.2 | 25.4 | 26.6 | 83.4 | 76.2 | 58.9 | 24.9 | 80.7 | 42.9 | 26.9 | 11.6 | 36.7 | 29.5 | 2.5 | |
| MADANStandard=Multi-source DA, Source Domain=GTA, SYNTHIA, Backbone=VGG-162019.10 | 41.4 | — | — | — | — | 86.2 | 37.7 | 79.1 | 20.1 | 17.8 | 15.5 | 14.5 | 21.4 | 78.5 | 73.4 | 49.7 | 16.8 | 77.8 | 28.3 | 17.7 | 27.5 | — | — | — | |
| DIRLSource Dataset=GTA5, Backbone=ResNet-502023.07 | 41.04 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| SAWSource Dataset=GTA5, Backbone=ResNet-502023.07 | 39.75 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| AdvStyleSource Dataset=GTA5, Backbone=ResNet-502023.07 | 39.62 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| ROADStandard=GTA-only DA, Source Domain=GTA, Backbone=VGG-162019.10 | 39 | — | — | — | — | 85.4 | 31.2 | 78.6 | 27.9 | 22.2 | 21.9 | 23.7 | 11.4 | 80.7 | 68.9 | 48.5 | 14.1 | 78 | 23.8 | 8.3 | 0 | — | — | — | |
| CyCADAStandard=GTA-only DA, Source Domain=GTA, Backbone=VGG-162019.10 | 38.7 | — | — | — | — | 85.2 | 37.2 | 76.5 | 21.8 | 15 | 23.8 | 22.9 | 21.5 | 80.5 | 60.7 | 50.5 | 9 | 76.9 | 28.2 | 4.5 | 0 | — | — | — | |
| AdaptSegStandard=GTA-only DA, Source Domain=GTA, Backbone=VGG-162019.10 | 38.3 | — | — | — | — | 87.3 | 29.8 | 78.6 | 21.1 | 18.2 | 22.5 | 21.5 | 11 | 79.7 | 71.3 | 46.8 | 6.5 | 80.1 | 26.9 | 10.6 | 0.3 | — | — | — | |
| GTRSource Dataset=GTA5, Backbone=ResNet-502023.07 | 37.53 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| DRPCSource Dataset=GTA5, Backbone=ResNet-502023.07 | 37.42 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CyCADAStandard=Source-combined DA, Source Domain=GTA+SYNTHIA, Backbone=VGG-162019.10 | 37.3 | — | — | — | — | 82.8 | 35.8 | 78.2 | 17.5 | 15.1 | 10.8 | 6.1 | 19.4 | 78.6 | 77.2 | 44.5 | 15.3 | 74.9 | 17 | 10.3 | 12.9 | — | — | — | |
| ISWSource Dataset=GTA5, Backbone=ResNet-502023.07 | 36.58 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| DCANStandard=GTA-only DA, Source Domain=GTA, Backbone=VGG-162019.10 | 36.2 | — | — | — | — | 82.3 | 26.7 | 77.4 | 23.7 | 20.5 | 20.4 | 30.3 | 11.1 | 81.3 | 67.8 | 44.5 | 7 | 73.8 | 31.4 | 8.2 | 0.7 | — | — | — | |
| ROADStandard=SYNTHIA-only DA, Source Domain=SYNTHIA, Backbone=VGG-162019.10 | 36.2 | — | — | — | — | 77.7 | 30 | 77.5 | 9.6 | 0.3 | 25.8 | 10.3 | 15.6 | 77.6 | 79.8 | 44.5 | 15.9 | 80.9 | 69.5 | 52.6 | 11.7 | — | — | — | |
| DCANStandard=SYNTHIA-only DA, Source Domain=SYNTHIA, Backbone=VGG-162019.10 | 35.4 | — | — | — | — | 79.9 | 30.4 | 70.8 | 1.6 | 0.6 | 22.3 | 6.7 | 23 | 76.9 | 73.9 | 41.9 | 16.7 | 61.7 | 11.5 | 10.3 | 38.6 | — | — | — | |
| IBNSource Dataset=GTA5, Backbone=ResNet-502023.07 | 33.85 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| IternormSource Dataset=GTA5, Backbone=ResNet-502023.07 | 31.81 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — |