Rethinking Noise-Robust Training for Frozen Vision Foundation Models: A Cross-Dataset Benchmark with a Case Study of Small-Loss Failure

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Zitong, Wang, Haoyu
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/2605.22591