[Re] Boosting the Visual Interpretability of CLIP via Adversarial Fine-Tuning

Anton Nuzhdin, Andrei Gruzitski, Balázs Egyed +1

This paper presents a reproducibility study of ``Boosting the Visual Interpretability of CLIP via Adversarial Fine-Tuning'', published at ICLR 2025, which proposes an unsupervised…