Cookies

We use cookies to ensure that we give you the best experience on our website. By continuing to browse this repository, you give consent for essential cookies to be used. You can read more about our Privacy and Cookie Policy.


Durham Research Online
You are in:

Skip-GANomaly: skip connected and adversarially trained encoder-decoder anomaly detection

Akcay, Akcay and Atapour-Abarghouei, Amir and Breckon, Toby P. (2019) 'Skip-GANomaly: skip connected and adversarially trained encoder-decoder anomaly detection.', in Proceedings of the International Joint Conference on Neural Networks. .

Abstract

Despite inherent ill-definition, anomaly detection is a research endeavour of great interest within machine learning and visual scene understanding alike. Most commonly, anomaly detection is considered as the detection of outliers within a given data distribution based on some measure of normality. The most significant challenge in real-world anomaly detection problems is that available data is highly imbalanced towards normality (i.e. non-anomalous) and contains at most a sub-set of all possible anomalous samples - hence limiting the use of well-established supervised learning methods. By contrast, we introduce an unsupervised anomaly detection model, trained only on the normal (non-anomalous, plentiful) samples in order to learn the normality distribution of the domain, and hence detect abnormality based on deviation from this model. Our proposed approach employs an encoder-decoder convolutional neural network with skip connections to thoroughly capture the multiscale distribution of the normal data distribution in image space. Furthermore, utilizing an adversarial training scheme for this chosen architecture provides superior reconstruction both within image space and a lower-dimensional embedding vector space encoding. Minimizing the reconstruction error metric within both the image and hidden vector spaces during training aids the model to learn the distribution of normality as required. Higher reconstruction metrics during subsequent test and deployment are thus indicative of a deviation from this normal distribution, hence indicative of an anomaly. Experimentation over established anomaly detection benchmarks and challenging real-world datasets, within the context of X-ray security screening, shows the unique promise of such a proposed approach.

Item Type:Book chapter
Full text:(AM) Accepted Manuscript
Download PDF
(8661Kb)
Status:Peer-reviewed
Publisher Web site:https://doi.org/10.1109/IJCNN.2019.8851808
Publisher statement:© 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Date accepted:07 March 2019
Date deposited:03 October 2019
Date of first online publication:30 September 2019
Date first made open access:29 November 2021

Save or Share this output

Export:
Export
Look up in GoogleScholar