Image Classification on Stanford Cars (Robust Accuracy)
22.25Robust AccuracyOurs (5 trees)
Evaluation results
| Method | Links | |
|---|---|---|
| Ours (5 trees)Zero-shot=true, Adversarial fine-tuning=ImageNet, PGD attack steps=20, Perturbation radius (epsilon)=1/255, Number of trees=52026.04 | 22.25 | |
| AoSZero-shot=true, Adversarial fine-tuning=ImageNet, PGD attack steps=20, Perturbation radius (epsilon)=1/2552026.04 | 21.25 | |
| OursZero-shot=true, Adversarial fine-tuning=ImageNet, PGD attack steps=20, Perturbation radius (epsilon)=1/2552026.04 | 20.88 | |
| FAREZero-shot=true, Adversarial fine-tuning=ImageNet, PGD attack steps=20, Perturbation radius (epsilon)=1/2552026.04 | 17.44 | |
| PMG-FTZero-shot=true, Adversarial fine-tuning=ImageNet, PGD attack steps=20, Perturbation radius (epsilon)=1/2552026.04 | 16.74 | |
| TeCoAZero-shot=true, Adversarial fine-tuning=ImageNet, PGD attack steps=20, Perturbation radius (epsilon)=1/2552026.04 | 13.08 | |
| CLIPZero-shot=true, Adversarial fine-tuning=ImageNet, PGD attack steps=20, Perturbation radius (epsilon)=1/2552026.04 | 0.27 |