most citedData Determines Distributional Robustness in Contrastive Language Image Pre-training (CLIP)

27 citations · 27 across the 1 of their papers we have counts for

collaborators

1 paper

cs.CV2022★ 27 cited

Data Determines Distributional Robustness in Contrastive Language Image Pre-training (CLIP)

Alex Fang, Gabriel Ilharco, Mitchell Wortsman +4

Contrastively trained language-image models such as CLIP, ALIGN, and BASIC have demonstrated unprecedented robustness to multiple challenging natural distribution shifts. Since the…