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...

Full description

Bibliographic Details

Published in:	IEEE transactions on knowledge and data engineering Vol. 37; no. 5; pp. 3001 - 3014
Main Authors:	Yasutomi, Suguru, Tanaka, Toshihisa
Format:	Journal Article
Language:	English
Published:	IEEE 01.05.2025
Subjects:	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 Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!