Multi Task Learning On Cityscapes
Metrics
RMSE
mIoU
Results
Performance results of various models on this benchmark
| Paper Title | |||
|---|---|---|---|
| SwinMTL | 0.51 | 76.41 | SwinMTL: A Shared Architecture for Simultaneous Depth Estimation and Semantic Segmentation from Monocular Camera Images |
| Nash-MTL | - | 75.41 | Multi-Task Learning as a Bargaining Game |
| MultiObjectiveOptimization | - | 66.63 | Multi-Task Learning as Multi-Objective Optimization |
0 of 3 row(s) selected.