Tag: Unsupervised Learning
All the articles with the tag "Unsupervised Learning".
-
Style Feature Extraction Using Contrastive Conditioned Variational Autoencoders with Mutual Information Constraints
This paper proposes a novel method combining contrastive learning with conditional variational autoencoders and mutual information constraints to extract style features from unlabeled data, demonstrating effectiveness on simple datasets like MNIST while facing challenges with natural image datasets due to augmentation limitations and qualitative evaluation.