ICML 2021
CLIP: Visual Models via Language Supervision
Alec Radford, Jong Wook Kim, +10
CLIP explained: contrastive learning on 400M image-text pairs enables zero-shot image classification and powerful vision-language understanding.
Explore machine learning papers and reviews related to CLIP. Find insights, analysis, and implementation details.
Alec Radford, Jong Wook Kim, +10
CLIP explained: contrastive learning on 400M image-text pairs enables zero-shot image classification and powerful vision-language understanding.