Three Heads Are Better Than One: Complementary Experts for Long-Tailed Semi-supervised Learning

We address the challenging problem of Long-Tailed Semi-Supervised Learning (LTSSL) where labeled data exhibit imbalanced class distribution and unlabeled data follow an unknown distribution. Unlike in balanced SSL, the generated pseudo-labels are skewed towards head classes, intensifying the trainin...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ma, Chengcheng, Elezi, Ismail, Deng, Jiankang, Dong, Weiming, Xu, Changsheng
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!