Skip to main content

Research Repository

Advanced Search

GANomaly: Semi-Supervised Anomaly Detection via Adversarial Training

Akcay, Samet; Atapour-Abarghouei, Amir; Breckon, Toby P.

GANomaly: Semi-Supervised Anomaly Detection via Adversarial Training Thumbnail


Authors

Samet Akcay samet.akcay@durham.ac.uk
PGR Student Doctor of Philosophy



Contributors

C.V. Jawahar
Editor

Hongdong Li
Editor

Greg Mori
Editor

Konrad Schindler
Editor

Abstract

Anomaly detection is a classical problem in computer vision, namely the determination of the normal from the abnormal when datasets are highly biased towards one class (normal) due to the insufficient sample size of the other class (abnormal). While this can be addressed as a supervised learning problem, a significantly more challenging problem is that of detecting the unknown/unseen anomaly case that takes us instead into the space of a one-class, semi-supervised learning paradigm. We introduce such a novel anomaly detection model, by using a conditional generative adversarial network that jointly learns the generation of high-dimensional image space and the inference of latent space. Employing encoder-decoder-encoder sub-networks in the generator network enables the model to map the input image to a lower dimension vector, which is then used to reconstruct the generated output image. The use of the additional encoder network maps this generated image to its latent representation. Minimizing the distance between these images and the latent vectors during training aids in learning the data distribution for the normal samples. As a result, a larger distance metric from this learned data distribution at inference time is indicative of an outlier from that distribution — an anomaly. Experimentation over several benchmark datasets, from varying domains, shows the model efficacy and superiority over previous state-of-the-art approaches.

Citation

Akcay, S., Atapour-Abarghouei, A., & Breckon, T. P. (2019). GANomaly: Semi-Supervised Anomaly Detection via Adversarial Training. In C. Jawahar, H. Li, G. Mori, & K. Schindler (Eds.), Computer Vision – ACCV 2018 : 14th Asian Conference on Computer Vision, Perth, Australia, December 2–6, 2018, Revised Selected Papers, Part III (622-637). https://doi.org/10.1007/978-3-030-20893-6_39

Conference Name 14th Asian Conference on Computer Vision (ACCV).
Conference Location Perth, Australia
Start Date Dec 2, 2018
End Date Dec 6, 2018
Acceptance Date Sep 18, 2018
Online Publication Date Dec 3, 2018
Publication Date 2019
Deposit Date Oct 8, 2018
Publicly Available Date Nov 15, 2018
Pages 622-637
Series Title Lecture notes in computer science
Series Number 11363
Series ISSN 0302-9743,1611-3349
Book Title Computer Vision – ACCV 2018 : 14th Asian Conference on Computer Vision, Perth, Australia, December 2–6, 2018, Revised Selected Papers, Part III.
ISBN 9783030208929
DOI https://doi.org/10.1007/978-3-030-20893-6_39
Public URL https://durham-repository.worktribe.com/output/1143807
Related Public URLs https://arxiv.org/abs/1805.06725

Files

Accepted Conference Proceeding (14.1 Mb)
PDF

Copyright Statement
This is a post-peer-review, pre-copyedit version of an article published in Computer Vision – ACCV 2018 : 14th Asian Conference on Computer Vision, Perth, Australia, December 2–6, 2018, Revised Selected Papers, Part III. The final authenticated version is available online at: https://doi.org/10.1007/978-3-030-20893-6_39





You might also like



Downloadable Citations