English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Unsupervised learning of anomaly detection in high-dimensional data, such asimages, is a challenging problem recently subject to intense research. Throughcareful modelling of the data distribution of normal samples, it is possible todetect deviant samples, so called anomalies. Generative Adversarial Networks(GANs) can model the highly complex, high-dimensional data distribution ofnormal image samples, and have shown to be a suitable approach to the problem.Previously published GAN-based anomaly detection methods often assume thatanomaly-free data is available for training. However, this assumption is notvalid in most real-life scenarios, a.k.a. in the wild. In this work, weevaluate the effects of anomaly contaminations in the training data onstate-of-the-art GAN-based anomaly detection methods. As expected, detectionperformance deteriorates. To address this performance drop, we propose to addan additional encoder network already at training time and show that jointgenerator-encoder training stratifies the latent space, mitigating the problemwith contaminated data. We show experimentally that the norm of a query imagein this stratified latent space becomes a highly significant cue todiscriminate anomalies from normal data. The proposed method achievesstate-of-the-art performance on CIFAR-10 as well as on a large, previouslyuntested dataset with cell images.

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