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, i.e. jointly learning from labeled and unlabeledsamples, is an active research topic due to its key role on relaxing humansupervision. In the context of image classification, recent advances to learnfrom unlabeled samples are mainly focused on consistency regularization methodsthat encourage invariant predictions for different perturbations of unlabeledsamples. We, conversely, propose to learn from unlabeled data by generatingsoft pseudo-labels using the network predictions. We show that a naivepseudo-labeling overfits to incorrect pseudo-labels due to the so-calledconfirmation bias and demonstrate that mixup augmentation and setting a minimumnumber of labeled samples per mini-batch are effective regularizationtechniques for reducing it. The proposed approach achieves state-of-the-artresults in CIFAR-10/100, SVHN, and Mini-ImageNet despite being much simplerthan other methods. These results demonstrate that pseudo-labeling alone canoutperform consistency regularization methods, while the opposite was supposedin previous work. Source code is available at https://git.io/fjQsC.

Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning