Learning with noisy labels via clean aware sharpness aware minimization

Learning with noisy labels via clean aware sharpness aware minimization

Abstract Noise label learning has attracted considerable attention owing to its ability to leverage large amounts of inexpensive and imprecise data. Sharpness aware minimization (SAM) has shown effective improvements in the generalization performance in the presence of noisy labels by introducing ad...

Full description

Saved in:
Bibliographic Details
Main Authors: Bin Huang, Ying Xie, Chaoyang Xu
Format: Article
Language:English
Published: Nature Portfolio 2025-01-01
Series:Scientific Reports
Subjects:
Deep neural networks
Noisy label learning
Sharpness aware minimization
Model generalization
Loss landscape
Online Access:https://doi.org/10.1038/s41598-025-85679-8
Tags: Add Tag
No Tags, Be the first to tag this record!

Internet

https://doi.org/10.1038/s41598-025-85679-8

Similar Items