[CVPR 2024] Validation-free few-shot adaptation of CLIP, using a well-initialized Linear Probe (ZSLP) and class-adaptive constraints (CLAP).
Why do you think that https://github.com/Understanding-Visual-Datasets/VisDiff is a good alternative to CLAP
[CVPR 2024] Validation-free few-shot adaptation of CLIP, using a well-initialized Linear Probe (ZSLP) and class-adaptive constraints (CLAP).
Why do you think that https://github.com/Understanding-Visual-Datasets/VisDiff is a good alternative to CLAP