Counterfactual Generation Framework for Few-Shot Learning

Few-shot learning (FSL) that aims to recognize novel classes with few labeled samples is troubled by its data scarcity. Though recent works tackle FSL with data augmentation-based methods, these models fail to maintain the discrimination and diversity of the generated samples due to the distribution...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on circuits and systems for video technology 2023-08, Vol.33 (8), p.1-1
Hauptverfasser:	Dang, Zhuohang, Luo, Minnan, Jia, Chengyou, Yan, Caixia, Chang, Xiaojun, Zheng, Qinghua
Format:	Artikel
Sprache:	eng
Schlagworte:	counterfactual inference Data augmentation Data mining Data models Feature extraction few-shot learning Generators Independent variables Inference Learning prototype learning Prototypes Semantics Task analysis
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!