List your company
ResearchFormerly WizWand

Depth Estimation on Virtual KITTI to Cityscapes 2 (val)

6.35RMSEFAMDA
6.11367.70939.30510.9007Sep 28, 2025
Updated 7mo ago

Evaluation results

MethodLinks
FAMDABackbone=DeepLabV2, UDA setting=True, Learning protocol (STL/MTL)=MTL2025.096.35
FAMDABackbone=SegFormer, UDA setting=True, Learning protocol (STL/MTL)=MTL2025.096.46
STL targetBackbone=DeepLabV2, UDA setting=False, Learning protocol (STL/MTL)=STL, Source/Target domain evaluation protocol=Target-supervised (Upper Bound)2025.096.62
MTL targetBackbone=DeepLabV2, UDA setting=False, Learning protocol (STL/MTL)=MTL, Source/Target domain evaluation protocol=Target-supervised (Upper Bound)2025.096.72
VTAGMLBackbone=Swin, UDA setting=True, Learning protocol (STL/MTL)=MTL2025.098.66
MulTBackbone=Swin, UDA setting=True, Learning protocol (STL/MTL)=MTL2025.0910.35
Swin-UDABackbone=Swin, UDA setting=True, Learning protocol (STL/MTL)=STL2025.0911.09
XTAMBackbone=DeepLabV2, UDA setting=True, Learning protocol (STL/MTL)=MTL2025.0911.15
STL-UDABackbone=DeepLabV2, UDA setting=True, Learning protocol (STL/MTL)=STL2025.0911.45
MTL-UDABackbone=DeepLabV2, UDA setting=True, Learning protocol (STL/MTL)=MTL2025.0911.85
STL sourceBackbone=DeepLabV2, UDA setting=False, Learning protocol (STL/MTL)=STL, Source/Target domain evaluation protocol=Source-only (No adaptation)2025.0911.99
MTL sourceBackbone=DeepLabV2, UDA setting=False, Learning protocol (STL/MTL)=MTL, Source/Target domain evaluation protocol=Source-only (No adaptation)2025.0912.26