Semantic Segmentation on Cityscapes source domain (train)
82.6mIoUGMMSeg-SegFormer
Evaluation results
| Method | Links | |
|---|---|---|
| GMMSeg-SegFormerExtra Resyn.=false, OOD Data=false, Backbone=MiT-B5 SegFormer, Generative formulation=true2022.10 | 82.6 | |
| GMMSeg-DeepLabv3+Extra Resyn.=false, OOD Data=false, Backbone=ResNet-101 DeepLabv3+, Generative formulation=true2022.10 | 81.1 | |
| SynthCPExtra Resyn.=true, OOD Data=false, Backbone=ResNet-101 DeepLabv3+2022.10 | 80.3 | |
| SynBoostExtra Resyn.=true, OOD Data=true, Backbone=ResNet-101 DeepLabv3+2022.10 | 80.3 | |
| MSPExtra Resyn.=false, OOD Data=false, Backbone=ResNet-101 DeepLabv3+2022.10 | 80.3 | |
| EntropyExtra Resyn.=false, OOD Data=false, Backbone=ResNet-101 DeepLabv3+2022.10 | 80.3 | |
| SMLExtra Resyn.=false, OOD Data=false, Backbone=ResNet-101 DeepLabv3+2022.10 | 80.3 | |
| MahalanobisExtra Resyn.=false, OOD Data=false, Backbone=ResNet-101 DeepLabv3+, Generative formulation=true2022.10 | 80.3 | |
| GMMSeg-FCNExtra Resyn.=false, OOD Data=false, Backbone=ResNet-101 FCN, Generative formulation=true2022.10 | 76.7 |