Adversarial Robustness Evaluation on Tiny-ImageNet LT
39Clean AccuracyAT-BSL-RA
Evaluation results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| AT-BSL-RABackbone=PreActResNet-18, Checkpoint=Best2024.03 | 39 | 18.82 | 16.94 | 14.26 | 14.6 | 12.73 | |
| AT-BSLBackbone=PreActResNet-18, Checkpoint=Best2024.03 | 38.83 | 17.47 | 15.34 | 13.35 | 14.08 | 11.83 | |
| ATBackbone=PreActResNet-18, Checkpoint=Best2024.03 | 36.3 | 16.58 | 14.52 | 12.65 | 13.16 | 11.37 | |
| RoBalBackbone=PreActResNet-18, Checkpoint=Best2024.03 | 36.27 | 13.66 | 10.98 | 10.18 | 9.84 | 8.98 |