Data determines distributional robustness in contrastive language image pre-training (clip)
作者： Alex Fang , Gabriel Ilharco , Mitchell Wortsman , Yuhao Wan , Vaishaal Shankar
DOI:
关键词:
摘要: Contrastively trained language-image models such as CLIP, ALIGN, and BASIC have demonstrated unprecedented robustness to multiple challenging natural distribution shifts …
参考文章(0)