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 improve the recently-proposed "MixMatch" semi-supervised learningalgorithm by introducing two new techniques: distribution alignment andaugmentation anchoring. Distribution alignment encourages the marginaldistribution of predictions on unlabeled data to be close to the marginaldistribution of ground-truth labels. Augmentation anchoring feeds multiplestrongly augmented versions of an input into the model and encourages eachoutput to be close to the prediction for a weakly-augmented version of the sameinput. To produce strong augmentations, we propose a variant of AutoAugmentwhich learns the augmentation policy while the model is being trained. Our newalgorithm, dubbed ReMixMatch, is significantly more data-efficient than priorwork, requiring between $5\times$ and $16\times$ less data to reach the sameaccuracy. For example, on CIFAR-10 with 250 labeled examples we reach $93.73\%$accuracy (compared to MixMatch's accuracy of $93.58\%$ with $4{,}000$ examples)and a median accuracy of $84.92\%$ with just four labels per class. We make ourcode and data open-source at https://github.com/google-research/remixmatch.

ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring