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

Adversarial training based on the maximum classifier discrepancy between twoclassifier structures has achieved great success in unsupervised domainadaptation tasks for image classification. The approach adopts the structure oftwo classifiers, though simple and intuitive, the learned classificationboundary may not well represent the data property in the new domain. In thispaper, we propose to extend the structure to multiple classifiers to furtherboost its performance. To this end, we develop a very straightforward approachto adding more classifiers. We employ the principle that the classifiers aredifferent from each other to construct a discrepancy loss function for multipleclassifiers. The proposed construction method of loss function makes itpossible to add any number of classifiers to the original framework. Theproposed approach is validated through extensive experimental evaluations. Wedemonstrate that, on average, adopting the structure of three classifiersnormally yields the best performance as a trade-off between accuracy andefficiency. With minimum extra computational costs, the proposed approach cansignificantly improve the performance of the original algorithm. The sourcecode of the proposed approach can be downloaded from\url{https://github.com/rucv/MMCD\_DA}.

Multiple Classifiers Based Maximum Classifier Discrepancy for Unsupervised Domain Adaptation