Context-encoding Variational Autoencoder for Unsupervised Anomaly Detection -- Short Paper

2019/07/29 by Zimmerer, David, Kohl, Simon, Petersen, Jens +2
#FOS: Electrical engineering #Image and Video Processing (eess.IV) #electronic engineering #information engineering

paper · doi:10.48550/arxiv.1907.12258

Abstract

Unsupervised learning can leverage large-scale data sources without the need for annotations. In this context, deep learning-based autoencoders have shown great potential in detecting anomalies in medical images. However, especially Variational Autoencoders (VAEs)often fail to capture the high-level structure in the data. We address these shortcomings by proposing the context-encoding Variational Autoencoder (ceVAE), which improves both, the sample, as well as pixelwise results. In our experiments on the BraTS-2017 and ISLES-2015 segmentation benchmarks the ceVAE achieves unsupervised AUROCs of 0.95 and 0.89, respectively, thus outperforming other reported deep-learning based approaches.

Related

• Context-encoding Variational Autoencoder for Unsupervised Anomaly Detection
• A Case for the Score: Identifying Image Anomalies using Variational Autoencoder Gradients
• Anomaly Detection for Skin Disease Images Using Variational Autoencoder
• Unsupervised Anomaly Localization using Variational Auto-Encoders
• Interpreting Rate-Distortion of Variational Autoencoder and Using Model Uncertainty for Anomaly Detection