Binary Classification on CIFAR-10 (Clean and Robust Accuracy)
68Clean AccuracyStandardly pretrained model
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Standardly pretrained modelArchitecture=single-layer linear transformer, Pre-training strategy=Standard2025.05 | 68 | 21 | |
| Adversarially pretrained modelArchitecture=single-layer linear transformer, Pre-training strategy=Adversarial2025.05 | 64 | 34 |