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

Deep neural networks have been successfully applied to many real-worldapplications. However, such successes rely heavily on large amounts of labeleddata that is expensive to obtain. Recently, many methods for semi-supervisedlearning have been proposed and achieved excellent performance. In this study,we propose a new EnAET framework to further improve existing semi-supervisedmethods with self-supervised information. To our best knowledge, all currentsemi-supervised methods improve performance with prediction consistency andconfidence ideas. We are the first to explore the role of {\bf self-supervised}representations in {\bf semi-supervised} learning under a rich family oftransformations. Consequently, our framework can integrate the self-supervisedinformation as a regularization term to further improve {\it all} currentsemi-supervised methods. In the experiments, we use MixMatch, which is thecurrent state-of-the-art method on semi-supervised learning, as a baseline totest the proposed EnAET framework. Across different datasets, we adopt the samehyper-parameters, which greatly improves the generalization ability of theEnAET framework. Experiment results on different datasets demonstrate that theproposed EnAET framework greatly improves the performance of currentsemi-supervised algorithms. Moreover, this framework can also improve {\bfsupervised learning} by a large margin, including the extremely challengingscenarios with only 10 images per class. The code and experiment records areavailable in \url{https://github.com/maple-research-lab/EnAET}.

EnAET: A Self-Trained framework for Semi-Supervised and Supervised Learning with Ensemble Transformations