Abstract: With its powerful visual-language alignment capability, CLIP performs well in zero-shot and few-shot learning tasks. However, we found in experiments that CLIP’s logits suffer from serious ...
Abstract: The development of large-scale image-text pair datasets has significantly advanced self-supervised learning in Vision-Language Processing (VLP). However, directly applying general-domain ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback