Fine-grained Image Classification on 10 Fine-grained Datasets Average
57Average AccuracyTPT
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| TPTBackbone=CLIP-ResNet50, Epsilon=1.0, Augmentation views=152026.06 | 57 | 1.2 | |
| CLIPBackbone=CLIP-ResNet50, Epsilon=1.02026.06 | 55.8 | 0.8 | |
| SS-TPTBackbone=CLIP-ResNet50, Epsilon=1.0, Augmentation views=152026.06 | 55.1 | 46.8 | |
| R-TPTBackbone=CLIP-ResNet50, Epsilon=1.0, Augmentation views=152026.06 | 54.2 | 40.4 | |
| EnsembleBackbone=CLIP-ResNet50, Epsilon=1.0, Augmentation views=152026.06 | 53.2 | 34.2 | |
| DOCBackbone=CLIP-ResNet50, Epsilon=1.0, Effective batch size=12026.06 | 52.1 | 13.6 | |
| TTCBackbone=CLIP-ResNet50, Epsilon=1.0, Effective batch size=12026.06 | 51.9 | 13.7 |