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

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ziyin, Liu, Chen, Blair, Wang, Ru, Liang, Paul Pu, Salakhutdinov, Ruslan, Morency, Louis-Philippe, Ueda, Masahito
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!