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

In this work, we present Con$^{2}$DA, a simple framework that extends recentadvances in semi-supervised learning to the semi-supervised domain adaptation(SSDA) problem. Our framework generates pairs of associated samples byperforming stochastic data transformations to a given input. Associated datapairs are mapped to a feature representation space using a feature extractor.We use different loss functions to enforce consistency between the featurerepresentations of associated data pairs of samples. We show that these learnedrepresentations are useful to deal with differences in data distributions inthe domain adaptation problem. We performed experiments to study the maincomponents of our model and we show that (i) learning of the consistent andcontrastive feature representations is crucial to extract good discriminativefeatures across different domains, and ii) our model benefits from the use ofstrong augmentation policies. With these findings, our method achievesstate-of-the-art performances in three benchmark datasets for SSDA.

Con$^{2}$DA: Simplifying Semi-supervised Domain Adaptation by Learning Consistent and Contrastive Feature Representations