Not All Attention Heads Are What You Need: Refining CLIP's Image Representation with Attention Ablation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lin, Feng, Chen, Marco, Zhang, Haokui, Yu, Xiaotian, Lu, Guangming, Xiao, Rong
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2507.00537