Unsupervised Learning of Anomaly Detection from Contaminated Image Data using Simultaneous Encoder Training

Abstract

Unsupervised learning of anomaly detection in high-dimensional data, such as images, is a challenging problem recently subject to intense research. Through careful modelling of the data distribution of normal samples, it is possible to detect deviant samples, so called anomalies. Generative Adversarial Networks (GANs) can model the highly complex, high-dimensional data distribution of normal image samples, and have shown to be a suitable approach to the problem. Previously published GAN-based anomaly detection methods often assume that anomaly-free data is available for training. However, this assumption is not valid in most real-life scenarios, a.k.a. in the wild. In this work, we evaluate the effects of anomaly contaminations in the training data on state-of-the-art GAN-based anomaly detection methods. As expected, detection performance deteriorates. To address this performance drop, we propose to add an additional encoder network already at training time and show that joint generator-encoder training stratifies the latent space, mitigating the problem with contaminated data. We show experimentally that the norm of a query image in this stratified latent space becomes a highly significant cue to discriminate anomalies from normal data. The proposed method achieves state-of-the-art performance on CIFAR-10 as well as on a large, previously untested dataset with cell images.

References in corpus (7)

• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Generative Adversarial Networks: An Overview
• Deep Learning for Anomaly Detection: A Survey
• Deep Anomaly Detection Using Geometric Transformations
• Adversarial Autoencoders
• Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery
• Fence GAN: Towards Better Anomaly Detection

Cited by in corpus (8)

• Machine Learning in Aerodynamic Shape Optimization
• SIGL: Securing Software Installations Through Deep Graph Learning
• Unsupervised Two-Stage Anomaly Detection
• Normality-Calibrated Autoencoder for Unsupervised Anomaly Detection on Data Contamination
• Unsupervised Anomaly Detection with Adversarial Mirrored AutoEncoders
• RSM-GAN: A Convolutional Recurrent GAN for Anomaly Detection in Contaminated Seasonal Multivariate Time Series
• Improving Robustness on Seasonality-Heavy Multivariate Time Series Anomaly Detection
• Unsupervised Region-based Anomaly Detection in Brain MRI with Adversarial Image Inpainting