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

Contrastive learning is a representation learning method performed bycontrasting a sample to other similar samples so that they are brought closelytogether, forming clusters in the feature space. The learning process istypically conducted using a two-stage training architecture, and it utilizesthe contrastive loss (CL) for its feature learning. Contrastive learning hasbeen shown to be quite successful in handling imbalanced datasets, in whichsome classes are overrepresented while some others are underrepresented.However, previous studies have not specifically modified CL for imbalanceddatasets. In this work, we introduce an asymmetric version of CL, referred toas ACL, in order to directly address the problem of class imbalance. Inaddition, we propose the asymmetric focal contrastive loss (AFCL) as a furthergeneralization of both ACL and focal contrastive loss (FCL). Results on theFMNIST and ISIC 2018 imbalanced datasets show that AFCL is capable ofoutperforming CL and FCL in terms of both weighted and unweightedclassification accuracies. In the appendix, we provide a full axiomatictreatment on entropy, along with complete proofs.

An Asymmetric Contrastive Loss for Handling Imbalanced Datasets