EVA: Bridging Performance and Human Alignment in Hard-Attention Vision Models for Image Classification

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Pan, Pengcheng, Shogo, Yonekura, Yasuo, Kuniyoshi
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2603.27340