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

As a kind of generative self-supervised learning methods, generativeadversarial nets have been widely studied in the field of anomaly detection.However, the representation learning ability of the generator is limited sinceit pays too much attention to pixel-level details, and generator is difficultto learn abstract semantic representations from label prediction pretext tasksas effective as discriminator. In order to improve the representation learningability of generator, we propose a self-supervised learning framework combininggenerative methods and discriminative methods. The generator no longer learnsrepresentation by reconstruction error, but the guidance of discriminator, andcould benefit from pretext tasks designed for discriminative methods. Ourdiscriminative-generative representation learning method has performance closeto discriminative methods and has a great advantage in speed. Our method usedin one-class anomaly detection task significantly outperforms severalstate-of-the-arts on multiple benchmark data sets, increases the performance ofthe top-performing GAN-based baseline by 6% on CIFAR-10 and 2% on MVTAD.

Discriminative-Generative Representation Learning for One-Class Anomaly Detection