English

High- and Low-level image component decomposition using VAEs for improved reconstruction and anomaly detection

Machine Learning 2019-11-28 v1 Computer Vision and Pattern Recognition Image and Video Processing Machine Learning

Abstract

Variational Auto-Encoders have often been used for unsupervised pretraining, feature extraction and out-of-distribution and anomaly detection in the medical field. However, VAEs often lack the ability to produce sharp images and learn high-level features. We propose to alleviate these issues by adding a new branch to conditional hierarchical VAEs. This enforces a division between higher-level and lower-level features. Despite the additional computational overhead compared to a normal VAE it results in sharper and better reconstructions and can capture the data distribution similarly well (indicated by a similar or slightly better OoD detection performance).

Keywords

Cite

@article{arxiv.1911.12161,
  title  = {High- and Low-level image component decomposition using VAEs for improved reconstruction and anomaly detection},
  author = {David Zimmerer and Jens Petersen and Klaus Maier-Hein},
  journal= {arXiv preprint arXiv:1911.12161},
  year   = {2019}
}
R2 v1 2026-06-23T12:29:00.154Z