Image Classification on CIFAR-10 SEP (test)
88.27Test AccuracyNonlinear transformation framework
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| Nonlinear transformation frameworkBackbone=VGG19, Pre-trained=True (ImageNet)2024.06 | 88.27 | 0.99 | 1.13 | |
| OPABackbone=VGG19, Pre-trained=True (ImageNet)2024.06 | 87.28 | — | — | |
| Adversarial trainingBackbone=VGG19, Pre-trained=True (ImageNet), Defense Method=PGD2024.06 | 87.2 | — | — | |
| No defenseBackbone=VGG19, Pre-trained=True (ImageNet)2024.06 | 23 | — | — |