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

Self-supervised representation learning is an emerging research topic for itspowerful capacity in learning with unlabeled data. As a mainstreamself-supervised learning method, augmentation-based contrastive learning hasachieved great success in various computer vision tasks that lack manualannotations. Despite current progress, the existing methods are often limitedby extra cost on memory or storage, and their performance still has large roomfor improvement. Here we present a self-supervised representation learningmethod, namely AAG, which is featured by an auxiliary augmentation strategy andGNT-Xent loss. The auxiliary augmentation is able to promote the performance ofcontrastive learning by increasing the diversity of images. The proposedGNT-Xent loss enables a steady and fast training process and yields competitiveaccuracy. Experiment results demonstrate the superiority of AAG to previousstate-of-the-art methods on CIFAR10, CIFAR100, and SVHN. Especially, AAGachieves 94.5% top-1 accuracy on CIFAR10 with batch size 64, which is 0.5%higher than the best result of SimCLR with batch size 1024.

AAG: Self-Supervised Representation Learning by Auxiliary Augmentation with GNT-Xent Loss