Image Classification on UCF101 (Top-1 Acc, ECE)
69.63Top-1 AccuracyARGTCA-DIV
Evaluation results
| Method | Links | ||
|---|---|---|---|
| ARGTCA-DIVPre-trained Backbone=CLIP Vit-B/16, Embedding dimension=1024-d2026.07 | 69.63 | 3.05 | |
| ARGTCA-DISCPre-trained Backbone=CLIP Vit-B/16, Embedding dimension=1024-d2026.07 | 68.7 | 3.81 | |
| A-TPTPre-trained Backbone=CLIP Vit-B/16, Embedding dimension=1024-d2026.07 | 67.64 | 6.11 | |
| TPTPre-trained Backbone=CLIP Vit-B/16, Embedding dimension=1024-d2026.07 | 67.27 | 13.01 | |
| TCAPre-trained Backbone=CLIP Vit-B/16, Embedding dimension=1024-d2026.07 | 66.9 | 5.25 | |
| O-TPTPre-trained Backbone=CLIP Vit-B/16, Embedding dimension=1024-d2026.07 | 66.9 | 3.56 | |
| C-TPTPre-trained Backbone=CLIP Vit-B/16, Embedding dimension=1024-d2026.07 | 59.7 | 3.89 |