Semi-Supervised Learning via Weight-aware Distillation under Class Distribution Mismatch

Semi-Supervised Learning (SSL) under class distribution mismatch aims to tackle a challenging problem wherein unlabeled data contain lots of unknown categories unseen in the labeled ones. In such mismatch scenarios, traditional SSL suffers severe performance damage due to the harmful invasion of the...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2023-08
Hauptverfasser:	Du, Pan, Zhao, Suyun, Sheng, Zisen, Li, Cuiping, Chen, Hong
Format:	Artikel
Sprache:	eng
Schlagworte:	Categories Classifiers Datasets Distillation Knowledge management Labels Representations Robustness (mathematics) Semi-supervised learning Upper bounds
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!