Image Classification on VisDA-C
92.1Mean AccuracySSA
Evaluation results
| Method | Links | |||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| SSASF=true, Backbone=ResNet-1012026.03 | 92.1 | — | — | 98.3 | 90 | 88 | 87.2 | 98.3 | 97.3 | 93.5 | 86.3 | 97.7 | 96.6 | 95.7 | 76.8 | |
| ProDeSF=true, Backbone=ResNet-1012026.03 | 91 | — | — | 98.3 | 92.4 | 86.6 | 80.5 | 98.1 | 98 | 92.3 | 84.3 | 94.7 | 97 | 94.1 | 75.6 | |
| ATPSF=true, Backbone=ResNet-1012026.03 | 89.3 | — | — | 97.6 | 91.8 | 88.7 | 73.1 | 97.6 | 92.9 | 92 | 95.7 | 93.4 | 89 | 87.9 | 71.3 | |
| WATT-SVisual Encoder=ViT-L/142024.06 | 89.26 | 91.71 | 86.8 | — | — | — | — | — | — | — | — | — | — | — | — | |
| WATT-SVisual Encoder=ViT-L/142024.06 | 89.26 | 91.71 | 86.8 | — | — | — | — | — | — | — | — | — | — | — | — | |
| TENTVisual Encoder=ViT-L/142024.06 | 88.59 | 91.4 | 85.77 | — | — | — | — | — | — | — | — | — | — | — | — | |
| TENTVisual Encoder=ViT-L/142024.06 | 88.59 | 91.4 | 85.77 | — | — | — | — | — | — | — | — | — | — | — | — | |
| CLIPARTTVisual Encoder=ViT-L/142024.06 | 88.48 | 91.34 | 85.61 | — | — | — | — | — | — | — | — | — | — | — | — | |
| CLIPARTTVisual Encoder=ViT-L/142024.06 | 88.48 | 91.34 | 85.61 | — | — | — | — | — | — | — | — | — | — | — | — | |
| CLIPVisual Encoder=ViT-L/142024.06 | 88.43 | 91.24 | 85.62 | — | — | — | — | — | — | — | — | — | — | — | — | |
| CLIPVisual Encoder=ViT-L/142024.06 | 88.43 | 91.24 | 85.62 | — | — | — | — | — | — | — | — | — | — | — | — | |
| TPTVisual Encoder=ViT-L/142024.06 | 88.03 | 90.65 | 85.41 | — | — | — | — | — | — | — | — | — | — | — | — | |
| TPTVisual Encoder=ViT-L/142024.06 | 88.03 | 90.65 | 85.41 | — | — | — | — | — | — | — | — | — | — | — | — | |
| WATT-SVisual Encoder=ViT-B/162024.06 | 87.24 | 87.72 | 86.75 | — | — | — | — | — | — | — | — | — | — | — | — | |
| TENTVisual Encoder=ViT-B/162024.06 | 87.19 | 87.57 | 86.81 | — | — | — | — | — | — | — | — | — | — | — | — | |
| WATT-PVisual Encoder=ViT-B/162024.06 | 87.14 | 87.61 | 86.66 | — | — | — | — | — | — | — | — | — | — | — | — | |
| CLIPARTTVisual Encoder=ViT-B/162024.06 | 87.09 | 87.58 | 86.6 | — | — | — | — | — | — | — | — | — | — | — | — | |
| CLIPVisual Encoder=ViT-B/162024.06 | 86.89 | 87.16 | 86.61 | — | — | — | — | — | — | — | — | — | — | — | — | |
| WATT-Sstrategy=Sequential MTWA2024.06 | 85.03 | 85.36 | 84.69 | — | — | — | — | — | — | — | — | — | — | — | — | |
| WATT-Pstrategy=Parallel MTWA2024.06 | 85 | 85.42 | 84.57 | — | — | — | — | — | — | — | — | — | — | — | — | |
| TPTVisual Encoder=ViT-B/162024.06 | 84.97 | 84.04 | 85.9 | — | — | — | — | — | — | — | — | — | — | — | — | |
| TENT2024.06 | 84.77 | 84.86 | 84.68 | — | — | — | — | — | — | — | — | — | — | — | — | |
| CLIPArTT2024.06 | 84.75 | 85.09 | 84.4 | — | — | — | — | — | — | — | — | — | — | — | — | |
| CLIP2024.06 | 84.44 | 84.43 | 84.45 | — | — | — | — | — | — | — | — | — | — | — | — | |
| RWOTSF=false, Backbone=ResNet-1012026.03 | 84 | — | — | 95.1 | 80.3 | 83.7 | 90 | 92.4 | 68 | 92.5 | 82.2 | 87.9 | 78.4 | 90.4 | 68.2 | |
| SHOTSF=true, Backbone=ResNet-1012026.03 | 82.9 | — | — | 94.3 | 88.5 | 80.1 | 57.3 | 93.1 | 94.9 | 80.7 | 80.3 | 91.5 | 89.1 | 86.3 | 58.2 | |
| STARSF=false, Backbone=ResNet-1012026.03 | 82.7 | — | — | 95 | 84 | 84.6 | 73 | 91.6 | 91.8 | 85.9 | 78.4 | 94.4 | 84.7 | 87 | 42.2 | |
| SSAScenario=Online adaptation2026.03 | 82.58 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| TPT2024.06 | 81.46 | 79.35 | 83.57 | — | — | — | — | — | — | — | — | — | — | — | — | |
| SHOTScenario=Online adaptation2026.03 | 76.69 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| TENTScenario=Online adaptation2026.03 | 75.43 | — | — | — | — | — | — | — | — | — | — | — | — | — | — |