Image Classification on CIFAR-10 Synthetic (test)
88.49Test AccuracyNonlinear transformation framework
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| Nonlinear transformation frameworkBackbone=VGG19, Pre-trained=True (ImageNet)2024.06 | 88.49 | 59 | 67 | |
| OPABackbone=VGG19, Pre-trained=True (ImageNet)2024.06 | 87.9 | — | — | |
| Adversarial trainingBackbone=VGG19, Pre-trained=True (ImageNet), Defense Method=PGD2024.06 | 86.74 | — | — | |
| No defenseBackbone=VGG19, Pre-trained=True (ImageNet)2024.06 | 13 | — | — |