Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
Anomaly Detection with Generative Adversarial Networks
Lucas Deecke, Robert Vandermeulen, Lukas Ruff, Stephan Mandt, Marius Kloft
Feb 15, 2018 (modified: Feb 15, 2018)ICLR 2018 Conference Blind Submissionreaders: everyoneShow Bibtex
Abstract:Many anomaly detection methods exist that perform well on low-dimensional problems however there is a notable lack of effective methods for high-dimensional spaces, such as images. Inspired by recent successes in deep learning we propose a novel approach to anomaly detection using generative adversarial networks. Given a sample under consideration, our method is based on searching for a good representation of that sample in the latent space of the generator; if such a representation is not found, the sample is deemed anomalous. We achieve state-of-the-art performance on standard image benchmark datasets and visual inspection of the most anomalous samples reveals that our method does indeed return anomalies.
TL;DR:We propose a method for anomaly detection with GANs by searching the generator's latent space for good sample representations.
Keywords:Anomaly Detection, Generative Adversarial Networks, Deep Learning, Inverse Problems
Enter your feedback below and we'll get back to you as soon as possible.