%0 Conference Paper %1 10.1007/978-3-030-10925-7_1 %A Deecke, Lucas %A Vandermeulen, Robert %A Ruff, Lukas %A Mandt, Stephan %A Kloft, Marius %B Machine Learning and Knowledge Discovery in Databases %C Cham %D 2019 %E Berlingerio, Michele %E Bonchi, Francesco %E Gärtner, Thomas %E Hurley, Neil %E Ifrim, Georgiana %I Springer International Publishing %K Anomaly_detection GAN %P 3--17 %T Image Anomaly Detection with Generative Adversarial Networks %X 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. %@ 978-3-030-10925-7

@inproceedings{10.1007/978-3-030-10925-7_1, 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.}, added-at = {2023-06-19T05:21:17.000+0200}, address = {Cham}, author = {Deecke, Lucas and Vandermeulen, Robert and Ruff, Lukas and Mandt, Stephan and Kloft, Marius}, biburl = {https://www.bibsonomy.org/bibtex/208f6cf1b44df4b6cfc693ff9a5577166/andolab}, booktitle = {Machine Learning and Knowledge Discovery in Databases}, editor = {Berlingerio, Michele and Bonchi, Francesco and G{\"a}rtner, Thomas and Hurley, Neil and Ifrim, Georgiana}, interhash = {8a8a789ced9d15ffa4d8a8c875253af8}, intrahash = {08f6cf1b44df4b6cfc693ff9a5577166}, isbn = {978-3-030-10925-7}, keywords = {Anomaly_detection GAN}, pages = {3--17}, publisher = {Springer International Publishing}, timestamp = {2023-06-19T05:21:17.000+0200}, title = {Image Anomaly Detection with Generative Adversarial Networks}, year = 2019 }