Depth Estimation on VKITTI2 -> Cityscapes (8 classes)
6.62RMSESTL target
Evaluation Results
| Method | Links | |
|---|---|---|
| STL targetArchitecture=Single-Task Learning, Strategy=Oracle (Target Labels)2022.06 | 6.62 | |
| MTL targetArchitecture=Multi-Task Learning, Strategy=Oracle (Target Labels)2022.06 | 6.72 | |
| mTEB (Ours)Architecture=Multi-Task Learning with mTEB, Strategy=Unsupervised Domain Adaptation2022.06 | 11.15 | |
| STL-UDAArchitecture=Single-Task Learning, Strategy=Unsupervised Domain Adaptation2022.06 | 11.45 | |
| MTL-UDAArchitecture=Multi-Task Learning, Strategy=Unsupervised Domain Adaptation2022.06 | 11.85 | |
| STL sourceArchitecture=Single-Task Learning, Strategy=Source only2022.06 | 11.99 | |
| MTL sourceArchitecture=Multi-Task Learning, Strategy=Source only2022.06 | 12.26 |