CMW-Net : Learning a Class-Aware Sample Weighting Mapping for Robust Deep Learning

Modern deep neural networks can easily overfit to biased training data containing corrupted labels or class imbalance. Sample re-weighting methods are popularly used to alleviate this data bias issue. Most current methods, however, require to manually pre-specify the weighting schemes relying on the...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on pattern analysis and machine intelligence. - 1979. - 45(2023), 10 vom: 01. Okt., Seite 11521-11539
1. Verfasser:	Shu, Jun (VerfasserIn)
Weitere Verfasser:	Yuan, Xiang, Meng, Deyu, Xu, Zongben
Format:	Online-Aufsatz
Sprache:	English
Veröffentlicht:	2023
Zugriff auf das übergeordnete Werk:	IEEE transactions on pattern analysis and machine intelligence
Schlagworte:	Journal Article