High- and Low-level image component decomposition using VAEs for improved reconstruction and anomaly detection
Zimmerer, David, Petersen, Jens, Maier-Hein, Klaus
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).
Nov-27-2019
- Country:
- North America
- United States (0.05)
- Canada (0.04)
- Europe > Germany
- Baden-Württemberg > Karlsruhe Region > Heidelberg (0.04)
- Asia > China
- North America
- Genre:
- Research Report (0.50)
- Industry:
- Health & Medicine (1.00)
- Technology: