A Closer Look at the Robustness of Contrastive Language-Image Pre-Training (CLIP) Weijie T u 1 Weijian Deng

Neural Information Processing Systems 

Contrastive Language-Image Pre-training (CLIP) models have demonstrated remarkable generalization capabilities across multiple challenging distribution shifts. However, there is still much to be explored in terms of their robustness to the variations of specific visual factors.

Similar Docs  Excel Report  more

TitleSimilaritySource
None found