Online Test-Time Adaptation on 11 VLM Downstream Datasets (test)
69.5Average Accuracy
StatA
Updated 4d ago
Evaluation Results
| Method | Links | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
2025.01 | 69.5 | 71.9 | 66 | 27.9 | 51.8 | 74.7 | 89.3 | 94.8 | 76.4 | 94.4 | 47 | 69.8 | |
2025.01 | 69.1 | 71.7 | 64.9 | 28.9 | 48.2 | 75.2 | 88.9 | 95.2 | 77.6 | 94.3 | 45.8 | 69 | |
2025.01 | 68.9 | 69.6 | 65.9 | 27.3 | 52.3 | 73.2 | 89.1 | 94.6 | 75.6 | 94.3 | 46.8 | 69.7 | |
2025.01 | 67.7 | 68.3 | 66 | 25.4 | 60.6 | 66.9 | 86.1 | 89.6 | 72.5 | 93.4 | 45.5 | 71 | |
2025.01 | 67.2 | 68 | 64.8 | 24.9 | 59.8 | 67 | 84.2 | 89.9 | 73.3 | 92.2 | 44.8 | 70.3 | |
2025.01 | 67.1 | 68.2 | 65.6 | 25.2 | 56.5 | 66.5 | 85.8 | 89.3 | 72.6 | 93.5 | 45.2 | 70.1 | |
2025.01 | 67 | 66.2 | 63.6 | 24.3 | 52.3 | 67.4 | 88 | 92.5 | 72.7 | 94.2 | 46.8 | 68.8 | |
2025.01 | 66.8 | 67.9 | 65.1 | 25.1 | 55.3 | 66.3 | 85.5 | 89 | 72.5 | 93.6 | 45.1 | 69.7 | |
2025.01 | 66.6 | 69.3 | 64.8 | 27.4 | 46.9 | 68 | 87.2 | 89.4 | 71.7 | 94 | 44.4 | 69 | |
2025.01 | 66.6 | 67.4 | 64.6 | 24.9 | 55.3 | 65.9 | 85.2 | 88.9 | 72.3 | 93.6 | 45 | 69.6 | |
2025.01 | 66.5 | 68 | 64.8 | 24.9 | 56.2 | 66.8 | 81.9 | 89 | 73 | 92.1 | 44.9 | 69.6 | |
2025.01 | 66.3 | 67.9 | 64.8 | 24.9 | 56.3 | 66.8 | 79.9 | 88.9 | 72.9 | 92.1 | 44.8 | 69.4 | |
2025.01 | 65.8 | 66.6 | 64.5 | 24.6 | 51.8 | 65.7 | 85.9 | 89.3 | 70.6 | 93.4 | 44 | 67.8 | |
2025.01 | 65.8 | 67.7 | 64.7 | 24.9 | 55.1 | 66.7 | 78.5 | 88 | 72.8 | 91.9 | 44.8 | 69 | |
2025.01 | 65.5 | 66.7 | 64.3 | 24.6 | 47.9 | 65.6 | 85.9 | 89.4 | 70.6 | 93.3 | 44 | 67.8 | |
2025.01 | 65.3 | 66.8 | 64.3 | 24.8 | 45.6 | 65.6 | 86.1 | 89.4 | 70.5 | 93.4 | 44 | 67.9 | |
2025.01 | 65.2 | 66.6 | 62.5 | 24.7 | 48.3 | 65.6 | 85.9 | 89.1 | 70.7 | 93.2 | 43.5 | 67.5 | |
2025.01 | 64.5 | 66.7 | 64.2 | 24.7 | 37 | 65.6 | 86.1 | 89.3 | 70.8 | 93.4 | 43.9 | 67.9 |