Semantic Segmentation on Cityscapes Cross-City (Tokyo) (val)
85.8Road IoUFADA
Evaluation results
| Method | Links | ||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| FADABackbone=DeepLab-v22020.07 | 85.8 | 39.5 | 76 | 14.7 | 24.9 | 84.6 | 91.7 | 62.2 | 27.7 | 71.4 | 3 | 29.3 | 56.3 | 51.3 | |
| Cross-CityBackbone=Dilation-Frontend2020.07 | 83.4 | 35.4 | 72.8 | 12.3 | 12.7 | 77.4 | 64.3 | 42.7 | 21.5 | 64.1 | 20.8 | 8.9 | 40.3 | 42.8 | |
| Source DeepLab-v2Backbone=DeepLab-v2, Adaptation=None2020.07 | 83.4 | 35.4 | 72.8 | 12.3 | 12.7 | 77.4 | 64.3 | 42.7 | 21.5 | 64.1 | 20.8 | 8.9 | 40.3 | 42.8 | |
| AdaptSegNetBackbone=DeepLab-v22020.07 | 81.5 | 26 | 77.8 | 17.8 | 26.8 | 82.7 | 90.9 | 55.8 | 38 | 72.1 | 4.2 | 24.5 | 50.8 | 49.9 | |
| Source Dilation-FrontendBackbone=Dilation-Frontend, Adaptation=None2020.07 | 81.2 | 26.7 | 71.7 | 8.7 | 5.6 | 73.2 | 75.7 | 39.3 | 14.9 | 57.6 | 19 | 1.6 | 33.8 | 39.2 |