Image Classification on DTD PGD-l2 attack, ε=0.5 (test)
66.49Robust AccuracyCore-tuning
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Core-tuningBackbone=ResNet-50, Pre-training=MoCo-v2, Attack Type=PGD-10, Perturbation Norm=l2, Epsilon=0.52021.02 | 66.49 | 72.94 | |
| AT-CE-ConBackbone=ResNet-50, Pre-training=MoCo-v2, Attack Type=PGD-10, Perturbation Norm=l2, Epsilon=0.52021.02 | 64.75 | 71.24 | |
| AT-CEBackbone=ResNet-50, Pre-training=MoCo-v2, Attack Type=PGD-10, Perturbation Norm=l2, Epsilon=0.52021.02 | 61.93 | 68.81 | |
| CEBackbone=ResNet-50, Pre-training=MoCo-v2, Attack Type=PGD-10, Perturbation Norm=l2, Epsilon=0.52021.02 | 42.25 | 71.68 |