Semantic Segmentation on Cityscapes -> Cross-City (Rio) (val)
80.6IoU (road)FADA
Evaluation results
| Method | Links | ||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| FADABackbone=DeepLab-v22020.07 | 80.6 | 53.4 | 84.2 | 5.8 | 23 | 78.4 | 87.7 | 60.2 | 26.4 | 77.1 | 37.6 | 53.7 | 42.3 | 54.7 | |
| Source DeepLab-v2Backbone=DeepLab-v2, Adaptation=None2020.07 | 76.6 | 47.3 | 82.5 | 12.6 | 22.5 | 77.9 | 86.5 | 43 | 19.8 | 74.5 | 36.8 | 29.4 | 16.7 | 48.2 | |
| AdaptSegNetBackbone=DeepLab-v22020.07 | 76.2 | 44.7 | 84.6 | 9.3 | 25.5 | 81.8 | 87.3 | 55.3 | 32.7 | 74.3 | 28.9 | 43 | 27.6 | 51.6 | |
| Cross-CityBackbone=Dilation-Frontend2020.07 | 74.2 | 43.9 | 79 | 2.4 | 7.5 | 77.8 | 69.5 | 39.3 | 10.3 | 67.9 | 41.2 | 27.9 | 10.9 | 42.5 | |
| Source Dilation-FrontendBackbone=Dilation-Frontend, Adaptation=None2020.07 | 69 | 31.8 | 77 | 4.7 | 3.7 | 71.8 | 80.8 | 38.2 | 8 | 61.2 | 38.9 | 11.5 | 3.4 | 38.5 |