Minimizing contrastive loss produces an orthogonal modality gap vector whose size is monotonically tied to robustness, so post-processing that reduces the gap improves robustness with no loss in clean accuracy.
Robust CLIP: Unsupervised adver- sarial fine-tuning of vision embeddings for robust large vision-language models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Is the Modality Gap a Bug or a Feature? A Robustness Perspective
Minimizing contrastive loss produces an orthogonal modality gap vector whose size is monotonically tied to robustness, so post-processing that reduces the gap improves robustness with no loss in clean accuracy.