Table 4.
Classification results (accuracy %) of different methods on VisDA2017 dataset. ResNet-101 is the backbone network. ↑ denotes an increase in performance. The bold number indicates the best performance.
| Methods | Plane | Bcybl | Bus | Car | Horse | Knife | Mcyle | Person | Plant | Sktbrd | Train | Truck | Avg |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| ResNet101 | 55.1 | 53.3 | 61.9 | 59.1 | 80.6 | 17.9 | 79.7 | 31.2 | 81.0 | 26.5 | 73.5 | 8.5 | 52.4 |
| DAN | 87.1 | 63.0 | 76.5 | 42.0 | 90.3 | 42.9 | 85.9 | 53.1 | 49.7 | 36.3 | 85.8 | 20.7 | 61.1 |
| MCD | 87.0 | 60.9 | 83.7 | 64.0 | 88.9 | 79.6 | 84.7 | 76.9 | 88.6 | 40.3 | 83.0 | 25.8 | 71.9 |
| BSP | 92.4 | 61.0 | 81.0 | 57.5 | 89.0 | 80.6 | 90.1 | 77.0 | 84.2 | 77.9 | 82.1 | 38.4 | 75.9 |
| ALDA | 93.8 | 74.1 | 82.4 | 69.4 | 90.6 | 87.2 | 89.0 | 67.6 | 93.4 | 76.1 | 87.7 | 22.2 | 77.8 |
| DWL | 90.7 | 80.2 | 86.1 | 67.6 | 92.4 | 81.5 | 86.8 | 78.0 | 90.6 | 57.1 | 85.6 | 28.7 | 77.1 |
| DANN | 81.9 | 77.7 | 82.8 | 44.3 | 81.2 | 29.5 | 65.1 | 28.6 | 51.9 | 54.6 | 82.8 | 7.8 | 57.4 |
| DANN+MRE | 90.0 ↑ | 69.5 | 75.9 | 48.2 ↑ | 86.8 ↑ | 28.8 | 91.5 ↑ | 75.9 | 91.1 ↑ | 66.9 ↑ | 88.0 ↑ | 46.3 ↑ | 71.6 ↑ |
| CDAN | 85.2 | 66.9 | 83.0 | 50.8 | 84.2 | 74.9 | 88.1 | 74.5 | 83.4 | 76.0 | 81.9 | 38.0 | 73.7 |
| CDAN+MRE | 95.1 ↑ | 71.7 ↑ | 85.6 ↑ | 71.2 ↑ | 91.4 ↑ | 89.5 ↑ | 92.9 ↑ | 80.0 ↑ | 91.2 ↑ | 83.3 ↑ | 88.1 ↑ | 46.3 ↑ | 82.2 ↑ |