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

Unsupervised domain adaptation aiming to learn a specific task for one domainusing another domain data has emerged to address the labeling issue insupervised learning, especially because it is difficult to obtain massiveamounts of labeled data in practice. The existing methods have succeeded byreducing the difference between the embedded features of both domains, but theperformance is still unsatisfactory compared to the supervised learning scheme.This is attributable to the embedded features that lay around each other but donot align perfectly and establish clearly separable clusters. We propose anovel domain adaptation method based on label propagation and cycle consistencyto let the clusters of the features from the two domains overlap exactly andbecome clear for high accuracy. Specifically, we introduce cycle consistency toenforce the relationship between each cluster and exploit label propagation toachieve the association between the data from the perspective of the manifoldstructure instead of a one-to-one relation. Hence, we successfully formedaligned and discriminative clusters. We present the empirical results of ourmethod for various domain adaptation scenarios and visualize the embeddedfeatures to prove that our method is critical for better domain adaptation.

Learning Condensed and Aligned Features for Unsupervised Domain Adaptation Using Label Propagation