| Paper | Code | Top 1 Accuracy | ModelName | ReleaseDate |
|---|---|---|---|---|
| Enhance the Visual Representation via Discrete Adversarial Training | ✓ Link | 32.77 | MAE+DAT (ViT-H) | 2022-09-16 |
| Improving Vision Transformers by Revisiting High-frequency Components | ✓ Link | 25.9 | VOLO-D5+HAT | 2022-04-03 |
| Discrete Representations Strengthen Vision Transformer Robustness | ✓ Link | 22.19 | DiscreteViT | 2021-11-20 |