Transductive inference has been widely investigated in few-shot image classification but completely overlooked in the recent fast growing literature on adapting vision-langage models like CLIP. This paper addresses the transductive zero-shot and few-shot CLIP classification challenge in which inference is...
Transductive zero-shot and few-shot CLIP This GitHub repository features code from our CVPR 2024 paper where we tackle zero-shot and few-shot classification using the vision-language model CLIP. Our approach handles groups of unlabeled images together, enhancing accuracy over traditional methods that...