abhijay9/attacking_perceptual_similarity_metrics
[TMLR 2023] as a featured article (spotlight :star2: or top 0.01% of the accepted papers). In this study, we systematically examine the robustness of both traditional and learned perceptual similarity metrics to imperceptible adversarial perturbations.
PythonBSD-2-Clause
Issues
- 2
Reverse attack on classic metrics
#1 opened by ZhengyuZhao