Tag: Unsupervised Learning
All the articles with the tag "Unsupervised Learning".
-
Style Feature Extraction Using Contrastive Conditioned Variational Autoencoders with Mutual Information Constraints
Published: at 10:25 AM
93.98 🤔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.
-
Test-time Correlation Alignment
Published: at 12:21 AM 93.31 🤔本文提出测试时相关性对齐（TCA）范式，通过构建伪源域相关性并应用线性变换对齐测试数据特征，显著提升测试时适应（TTA）性能，同时保持高效性和源域知识。
-
Empirical Evaluation of Progressive Coding for Sparse Autoencoders
Published: at 04:33 PM 51.36 🤔本文通过实证评估比较了Matryoshka SAEs和基于字典幂律修剪的方法，以实现SAEs的渐进式编码，提高计算效率、重建保真度和可解释性。