Image Classification on ImageNet-R (Accuracy and Robustness Metrics)
69.2AccuracyMTA
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| MTACategory=Tuning-free, Backbone=CLIP-ViT-B/32, Attack scenario=PGD-100 (eps=4.0)2026.06 | 69.2 | 32.8 | |
| R-TPTCategory=Tuning-based, Backbone=CLIP-ViT-B/32, Attack scenario=PGD-100 (eps=4.0)2026.06 | 69 | 49.8 | |
| MACCategory=Tuning-free, Backbone=CLIP-ViT-B/32, Attack scenario=PGD-100 (eps=4.0)2026.06 | 65.5 | 55.2 | |
| CLIPCategory=Baseline, Backbone=CLIP-ViT-B/32, Attack scenario=PGD-100 (eps=4.0)2026.06 | 65.4 | 0 | |
| TTCCategory=Tuning-free, Backbone=CLIP-ViT-B/32, Attack scenario=PGD-100 (eps=4.0)2026.06 | 61.3 | 8.4 | |
| TPT2026.06 | 58.4 | 1.8 | |
| SS-TPT2026.06 | 56.3 | 46.7 | |
| CLIP2026.06 | 56.1 | 0.9 | |
| R-TPT2026.06 | 55.9 | 39.8 | |
| DOC2026.06 | 54.2 | 16.8 | |
| TTC2026.06 | 53.8 | 16.7 | |
| Ensemble2026.06 | 51.3 | 33.6 |