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

arXiv: https://arxiv.org/abs/1911.12161 · HTML: https://mlsanity.com/paper/1911.12161/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Nov 2019.

## Built on by (most cited first, 3 of 3)

- [CVAD: A generic medical anomaly detector based on Cascade VAE](https://mlsanity.com/paper/2110.15811/) (2021)
- [OCSVM-Guided Representation Learning for Unsupervised Anomaly Detection](https://mlsanity.com/paper/2507.21164/) (2025)
- [Unsupervised Hybrid framework for ANomaly Detection (HAND) -- applied to Screening Mammogram](https://mlsanity.com/paper/2409.11534/) (2024)

## Abstract (arXiv)

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).