Back to Search Start Over

CMW-Net: an adaptive robust algorithum for sample selection and label correction

Authors :
Jun Shu
Xiang Yuan
Deyu Meng
Source :
National Science Review.
Publication Year :
2023
Publisher :
Oxford University Press (OUP), 2023.

Abstract

A class-aware sample weighting algorithm is developed for general label noise problems. The algorithm can effectively tackle complicated and diverse noisy label tasks, winning the Championship of the ‘Arena Contest’ Track 1 of 2022 Greater BayArea (Huangpu) International Algorithm Case Competition.

Subjects

Subjects :
Multidisciplinary

Details

ISSN :
2053714X and 20955138
Database :
OpenAIRE
Journal :
National Science Review
Accession number :
edsair.doi...........1fac52de90a253cbf53440f0353ab4e6
Full Text :
https://doi.org/10.1093/nsr/nwad084