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

Semi-supervised learning has achieved notable success by leveraging very fewlabeled data and exploiting the wealth of information derived from unlabeleddata. However, existing algorithms usually focus on aligning predictions onpaired data points augmented from an identical source, and overlook theinter-point relationships within each batch. This paper introduces a novelmethod, RelationMatch, which exploits in-batch relationships with a matrixcross-entropy (MCE) loss function. Through the application of MCE, our proposedmethod consistently surpasses the performance of established state-of-the-artmethods, such as FixMatch and FlexMatch, across a variety of vision datasets.Notably, we observed a substantial enhancement of 15.21% in accuracy overFlexMatch on the STL-10 dataset using only 40 labels. Moreover, we apply MCE tosupervised learning scenarios, and observe consistent improvements as well.

RelationMatch: Matching In-batch Relationships for Semi-supervised Learning