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

Semi-supervised learning (SSL) aims to leverage massive unlabeled data whenlabels are expensive to obtain. Unfortunately, in many real-world applications,the collected unlabeled data will inevitably contain unseen-class outliers notbelonging to any of the labeled classes. To deal with the challenging open-setSSL task, the mainstream methods tend to first detect outliers and then filterthem out. However, we observe a surprising fact that such approach could resultin more severe performance degradation when labels are extremely scarce, as theunreliable outlier detector may wrongly exclude a considerable portion ofvaluable inliers. To tackle with this issue, we introduce a novel open-set SSLframework, IOMatch, which can jointly utilize inliers and outliers, even whenit is difficult to distinguish exactly between them. Specifically, we proposeto employ a multi-binary classifier in combination with the standard closed-setclassifier for producing unified open-set classification targets, which regardall outliers as a single new class. By adopting these targets as open-setpseudo-labels, we optimize an open-set classifier with all unlabeled samplesincluding both inliers and outliers. Extensive experiments have shown thatIOMatch significantly outperforms the baseline methods across differentbenchmark datasets and different settings despite its remarkable simplicity.Our code and models are available at https://github.com/nukezil/IOMatch.

IOMatch: Simplifying Open-Set Semi-Supervised Learning with Joint Inliers and Outliers Utilization