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).
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}
}