List your company
ResearchFormerly WizWand

Depth Estimation on SYNTHIA to Cityscapes (val)

6.29RMSEFAMDA
5.96128.180610.412.6194Sep 28, 2025
Updated 7mo ago

Evaluation results

MethodLinks
FAMDABackbone=DeepLabV2, UDA setting=True, Learning protocol (STL/MTL)=MTL2025.096.29
FAMDABackbone=SegFormer, UDA setting=True, Learning protocol (STL/MTL)=MTL2025.096.49
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)2025.096.79
VTAGMLBackbone=Swin, UDA setting=True, Learning protocol (STL/MTL)=MTL2025.096.99
MulTBackbone=Swin, UDA setting=True, Learning protocol (STL/MTL)=MTL2025.099.55
Swin-UDABackbone=Swin, UDA setting=True, Learning protocol (STL/MTL)=STL2025.0911.03
XTAMBackbone=DeepLabV2, UDA setting=True, Learning protocol (STL/MTL)=MTL2025.0911.66
STL sourceBackbone=DeepLabV2, UDA setting=False, Learning protocol (STL/MTL)=STL, Source/Target domain evaluation protocol=Source-only (No adaptation)2025.0913.79
STL-UDABackbone=DeepLabV2, UDA setting=True, Learning protocol (STL/MTL)=STL2025.0914.26
MTL-UDABackbone=DeepLabV2, UDA setting=True, Learning protocol (STL/MTL)=MTL2025.0914.47
MTL sourceBackbone=DeepLabV2, UDA setting=False, Learning protocol (STL/MTL)=MTL, Source/Target domain evaluation protocol=Source-only (No adaptation)2025.0914.51