Discrete Adversarial Distillation (ViT-B, 224)

Reported on 3 benchmarks across 3 tasks · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision2 results

Image ClassificationonImageNet V2
Top 1 Accuracy· 2023-11-02
71.7
best: 84.63 (Model soups (BASIC-L))
Distilling Out-of-Distribution Robustness from Vision-Language Foundation Models arXiv:2311.01441
Domain GeneralizationonImageNet-Sketch
Top-1 accuracy· 2023-11-02
46.1
best: 77.18 (Model soups (BASIC-L))
Distilling Out-of-Distribution Robustness from Vision-Language Foundation Models arXiv:2311.01441

Methodology1 result

Domain AdaptationonImageNet-Sketch
Top-1 accuracy· 2023-11-02
46.1
best: 77.18 (Model soups (BASIC-L))
Distilling Out-of-Distribution Robustness from Vision-Language Foundation Models arXiv:2311.01441