astra-vision/ProLIP

[WACV 2026] An extremely simple method for validation-free efficient adaptation of CLIP-like VLMs that is robust to the learning rate.

语言：Shell · GitHub 星标：41 · Fork：3

话题：contrastive-language-image-pretraining · few-shot-classifcation · open-classification · parameter-efficient-fine-tuning · test-time-adaptation · vision-language-model

在 GitHub 上查看原仓库