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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Contrastive learning has shown to learn better quality representations thanmodels trained using cross-entropy loss. They also transfer better todownstream datasets from different domains. However, little work has been doneto explore the transferability of representations learned using contrastivelearning when trained on a multi-domain dataset. In this paper, a study hasbeen conducted using the Supervised Contrastive Learning framework to learnrepresentations from the multi-domain DomainNet dataset and then evaluate thetransferability of the representations learned on other downstream datasets.The fixed feature linear evaluation protocol will be used to evaluate thetransferability on 7 downstream datasets that were chosen across differentdomains. The results obtained are compared to a baseline model that was trainedusing the widely used cross-entropy loss. Empirical results from theexperiments showed that on average, the Supervised Contrastive Learning modelperformed 6.05% better than the baseline model on the 7 downstream datasets.The findings suggest that Supervised Contrastive Learning models canpotentially learn more robust representations that transfer better acrossdomains than cross-entropy models when trained on a multi-domain dataset.

Transferability of Representations Learned using Supervised Contrastive Learning Trained on a Multi-Domain Dataset