OMASGAN: Out-of-distribution Minimum Anomaly Score GAN for Anomaly Detection

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

Generative models trained in an unsupervised manner may set high likelihood and low reconstruction loss to Out-of-Distribution (OoD) samples. This leads to failures to detect anomalies, overall decreasing Anomaly Detection (AD) performance. In addition, AD models underperform due to the rarity of anomalies. To address these limitations, we develop the OoD Minimum Anomaly Score GAN (OMASGAN) which performs retraining by including the proposed minimum-anomaly-score OoD samples. These OoD samples are generated on the boundary of the support of the normal class data distribution in a proposed self-supervised learning manner. Our OMASGAN retraining algorithm leads to more accurate estimation of the underlying data distribution including multimodal supports and also disconnected modes. For inference, for AD, we devise a discriminator which is trained with negative and positive samples either generated (negative or positive) or real (only positive). The evaluation of OMASGAN on image data using the leave-one-out method shows that it achieves an improvement of at least 0.24 and 0.07 points in AUROC on average on the MNIST and CIFAR-10 datasets, respectively, over other benchmark models for AD.
Original languageEnglish
Title of host publication2022 Sensor Signal Processing for Defence Conference (SSPD)
ISBN (Electronic)978-1-6654-8348-3
ISBN (Print)978-1-6654-8347-6
Publication statusE-pub ahead of print - 23 Sept 2022
EventInternational Conference in Sensor Signal Processing for Defence: : from Sensor to Decision - The Royal College of Physicians , Edinburgh, United Kingdom
Duration: 14 Sept 202115 Sept 2021


ConferenceInternational Conference in Sensor Signal Processing for Defence:
Abbreviated titleSSPD2021
Country/TerritoryUnited Kingdom
Internet address

Keywords / Materials (for Non-textual outputs)

  • Out-of-Distribution (OoD) detection
  • Anomaly detection
  • Generative Adversarial Networks (GAN)
  • Machine learning


Dive into the research topics of 'OMASGAN: Out-of-distribution Minimum Anomaly Score GAN for Anomaly Detection'. Together they form a unique fingerprint.

Cite this