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 Plus annual

Presents the access of premium content as premium feature

Premium Content

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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Anomaly detection (AD), separating anomalies from normal data, has manyapplications across domains, from security to healthcare. While most previousworks were shown to be effective for cases with fully or partially labeleddata, that setting is in practice less common due to labeling beingparticularly tedious for this task. In this paper, we focus on fullyunsupervised AD, in which the entire training dataset, containing both normaland anomalous samples, is unlabeled. To tackle this problem effectively, wepropose to improve the robustness of one-class classification trained onself-supervised representations using a data refinement process. Our proposeddata refinement approach is based on an ensemble of one-class classifiers(OCCs), each of which is trained on a disjoint subset of training data.Representations learned by self-supervised learning on the refined data areiteratively updated as the data refinement improves. We demonstrate our methodon various unsupervised AD tasks with image and tabular data. With a 10%anomaly ratio on CIFAR-10 image data / 2.5% anomaly ratio on Thyroid tabulardata, the proposed method outperforms the state-of-the-art one-class classifierby 6.3 AUC and 12.5 average precision / 22.9 F1-score.

Self-supervise, Refine, Repeat: Improving Unsupervised Anomaly Detection