%0 Conference Paper %1 10.5555/3327546.3327644GeometricTransformation %A Golan, Izhak %A El-Yaniv, Ran %B Proceedings of the 32nd International Conference on Neural Information Processing Systems %C Red Hook, NY, USA %D 2018 %I Curran Associates Inc. %K Anomaly Deep Detection %P 9781–9791 %T Deep Anomaly Detection Using Geometric Transformations %X We consider the problem of anomaly detection in images, and present a new detection technique. Given a sample of images, all known to belong to a "normal" class (e.g., dogs), we show how to train a deep neural model that can detect out-of-distribution images (i.e., non-dog objects). The main idea behind our scheme is to train a multi-class model to discriminate between dozens of geometric transformations applied on all the given images. The auxiliary expertise learned by the model generates feature detectors that effectively identify, at test time, anomalous images based on the softmax activation statistics of the model when applied on transformed images. We present extensive experiments using the proposed detector, which indicate that our technique consistently improves all known algorithms by a wide margin.

@inproceedings{10.5555/3327546.3327644GeometricTransformation, abstract = {We consider the problem of anomaly detection in images, and present a new detection technique. Given a sample of images, all known to belong to a "normal" class (e.g., dogs), we show how to train a deep neural model that can detect out-of-distribution images (i.e., non-dog objects). The main idea behind our scheme is to train a multi-class model to discriminate between dozens of geometric transformations applied on all the given images. The auxiliary expertise learned by the model generates feature detectors that effectively identify, at test time, anomalous images based on the softmax activation statistics of the model when applied on transformed images. We present extensive experiments using the proposed detector, which indicate that our technique consistently improves all known algorithms by a wide margin.}, added-at = {2023-12-01T17:19:17.000+0100}, address = {Red Hook, NY, USA}, author = {Golan, Izhak and El-Yaniv, Ran}, biburl = {https://www.bibsonomy.org/bibtex/2c46b13b863f182c2bb6ebe111e083247/andolab}, booktitle = {Proceedings of the 32nd International Conference on Neural Information Processing Systems}, interhash = {8158b9a68f9cf4cc8a5b18e25383280b}, intrahash = {c46b13b863f182c2bb6ebe111e083247}, keywords = {Anomaly Deep Detection}, location = {Montr\'{e}al, Canada}, numpages = {11}, pages = {9781–9791}, publisher = {Curran Associates Inc.}, series = {NIPS'18}, timestamp = {2023-12-01T17:19:17.000+0100}, title = {Deep Anomaly Detection Using Geometric Transformations}, year = 2018 }