Domain Generalization On Stylized Imagenet
Metriken
Top 1 Accuracy
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
| Paper Title | ||
|---|---|---|
| MAE+DAT (ViT-H) | 32.77 | Enhance the Visual Representation via Discrete Adversarial Training |
| VOLO-D5+HAT | 25.9 | Improving Vision Transformers by Revisiting High-frequency Components |
| DiscreteViT | 22.19 | Discrete Representations Strengthen Vision Transformer Robustness |
0 of 3 row(s) selected.