Unsupervised Learning of Anomaly Detection from Contaminated Image Data using Simultaneous Encoder Training
This addresses a practical issue for real-world applications where anomaly-free data is unavailable, though it is an incremental improvement over existing GAN-based approaches.
The paper tackles the problem of unsupervised anomaly detection in images when training data is contaminated with anomalies, which degrades performance in existing GAN-based methods. The proposed method adds an encoder during training to stratify the latent space, achieving state-of-the-art results on CIFAR-10 and a new cell image dataset.
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.