xmed-lab/CLIP_Surgery

[Pattern Recognition 25] CLIP Surgery for Better Explainability with Enhancement in Open-Vocabulary Tasks

⭐ 482 ⑂ 30 Jupyter Notebook · 2025-03-01推送

clip multimodal sam segment-anything segmentation vision-transformer explainability interpretability multilabel open-vocabulary

482

Watchers

0

贡献者

0

Commits

0

Releases

3

Open Issues

2025-03-01

最近推送

原文中文

暂无 README