Style Feature Extraction Using Contrastive Conditioned Variational Autoencoders With Mutual Information Constraints

Extracting fine-grained features such as styles from unlabeled data is crucial for data analysis. Unsupervised methods such as variational autoencoders (VAEs) can extract styles that are usually mixed with other features. Conditional VAEs (CVAEs) can isolate styles using class labels; however, there...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on knowledge and data engineering Jg. 37; H. 5; S. 3001 - 3014
Hauptverfasser:	Yasutomi, Suguru, Tanaka, Toshihisa
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	IEEE 01.05.2025
Schlagworte:	Autoencoders contrastive learning Data augmentation Data mining Data models Feature extraction Mutual information Perturbation methods Style extraction Training Unsupervised learning variational autoencoders Vectors
ISSN:	1041-4347, 1558-2191
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!