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/

Zendy Plus

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

Zendy Tools

Zendy Open

Domain adaptation (DA) aims to transfer knowledge learned from a labeledsource domain to an unlabeled or a less labeled but related target domain.Ideally, the source and target distributions should be aligned to each otherequally to achieve unbiased knowledge transfer. However, due to the significantimbalance between the amount of annotated data in the source and targetdomains, usually only the target distribution is aligned to the source domain,leading to adapting unnecessary source specific knowledge to the target domain,i.e., biased domain adaptation. To resolve this problem, in this work, we delveinto the transferability estimation problem in domain adaptation and propose anon-intrusive Unbiased Transferability Estimation Plug-in (UTEP) by modelingthe uncertainty of a discriminator in adversarial-based DA methods to optimizeunbiased transfer. We theoretically analyze the effectiveness of the proposedapproach to unbiased transferability learning in DA. Furthermore, to alleviatethe impact of imbalanced annotated data, we utilize the estimated uncertaintyfor pseudo label selection of unlabeled samples in the target domain, whichhelps achieve better marginal and conditional distribution alignments betweendomains. Extensive experimental results on a high variety of DA benchmarkdatasets show that the proposed approach can be readily incorporated intovarious adversarial-based DA methods, achieving state-of-the-art performance.

Learning Unbiased Transferability for Domain Adaptation by Uncertainty Modeling