Attention Transfer Is Not Universally Effective for Vision Transformers

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Qin, Huaiyuan, Yang, Muli, Goenawan, Gabriel James, Hu, Peng, Gong, Chen, Peng, Xi, Zhu, Hongyuan
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2605.07191