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

We introduce MarginMatch, a new SSL approach combining consistencyregularization and pseudo-labeling, with its main novelty arising from the useof unlabeled data training dynamics to measure pseudo-label quality. Instead ofusing only the model's confidence on an unlabeled example at an arbitraryiteration to decide if the example should be masked or not, MarginMatch alsoanalyzes the behavior of the model on the pseudo-labeled examples as thetraining progresses, to ensure low quality predictions are masked out.MarginMatch brings substantial improvements on four vision benchmarks in lowdata regimes and on two large-scale datasets, emphasizing the importance ofenforcing high-quality pseudo-labels. Notably, we obtain an improvement inerror rate over the state-of-the-art of 3.25% on CIFAR-100 with only 25 labelsper class and of 3.78% on STL-10 using as few as 4 labels per class. We makeour code available at https://github.com/tsosea2/MarginMatch.

MarginMatch: Improving Semi-Supervised Learning with Pseudo-Margins