Learning Not to Learn in the Presence of Noisy Labels

Learning in the presence of label noise is a challenging yet important task: it is crucial to design models that are robust in the presence of mislabeled datasets. In this paper, we discover that a new class of loss functions called the gambler's loss provides strong robustness to label noise a...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2020-02
Hauptverfasser:	Liu Ziyin, Chen, Blair, Wang, Ru, Paul Pu Liang, Salakhutdinov, Ruslan, Louis-Philippe Morency, Ueda, Masahito
Format:	Artikel
Sprache:	eng
Schlagworte:	Data points Image classification Labels Learning Noise Robustness Training
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!