Image Anomaly Detection with Generative Adversarial Networks
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.
Cite
Text
Deecke et al. "Image Anomaly Detection with Generative Adversarial Networks." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2018. doi:10.1007/978-3-030-10925-7_1Markdown
[Deecke et al. "Image Anomaly Detection with Generative Adversarial Networks." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2018.](https://mlanthology.org/ecmlpkdd/2018/deecke2018ecmlpkdd-image/) doi:10.1007/978-3-030-10925-7_1BibTeX
@inproceedings{deecke2018ecmlpkdd-image,
title = {{Image Anomaly Detection with Generative Adversarial Networks}},
author = {Deecke, Lucas and Vandermeulen, Robert A. and Ruff, Lukas and Mandt, Stephan and Kloft, Marius},
booktitle = {European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases},
year = {2018},
pages = {3-17},
doi = {10.1007/978-3-030-10925-7_1},
url = {https://mlanthology.org/ecmlpkdd/2018/deecke2018ecmlpkdd-image/}
}