VeCLIP: Improving CLIP Training via Visual-enriched Captions
Paper summary: Massive-scale web-crawled datasets are basic for the success of pre-training vision-language fashions, akin to CLIP. Nonetheless, the inherent ...
Tag: VeCLIP
Paper summary: Massive-scale web-crawled datasets are basic for the success of pre-training vision-language fashions, akin to CLIP. Nonetheless, the inherent ...