High- and Low-level image component decomposition using VAEs for improved reconstruction and anomaly detection
arXiv:1911.12161
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).
References in corpus (5)
- Auto-Encoding Variational Bayes
- Stochastic Backpropagation and Approximate Inference in Deep Generative Models
- Deep Autoencoding Models for Unsupervised Anomaly Segmentation in Brain MR Images
- Generating Diverse High-Fidelity Images with VQ-VAE-2
- Deep Generative Models in the Real-World: An Open Challenge from Medical Imaging