Recent advances in variational autoencoders with representation learning for biomedical informatics: A survey

R Wei, A Mahmood - Ieee Access, 2020 - ieeexplore.ieee.org
Variational autoencoders (VAEs) are deep latent space generative models that have been
immensely successful in multiple exciting applications in biomedical informatics such as …

Self-supervised learning disentangled group representation as feature

T Wang, Z Yue, J Huang, Q Sun… - Advances in Neural …, 2021 - proceedings.neurips.cc
A good visual representation is an inference map from observations (images) to features
(vectors) that faithfully reflects the hidden modularized generative factors (semantics). In this …