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

To deal with the domain shift between training and test samples, currentmethods have primarily focused on learning generalizable features duringtraining and ignore the specificity of unseen samples that are also criticalduring the test. In this paper, we investigate a more challenging task thataims to adapt a trained CNN model to unseen domains during the test. Tomaximumly mine the information in the test data, we propose a unified methodcalled DomainAdaptor for the test-time adaptation, which consists of anAdaMixBN module and a Generalized Entropy Minimization (GEM) loss.Specifically, AdaMixBN addresses the domain shift by adaptively fusing trainingand test statistics in the normalization layer via a dynamic mixturecoefficient and a statistic transformation operation. To further enhance theadaptation ability of AdaMixBN, we design a GEM loss that extends the EntropyMinimization loss to better exploit the information in the test data. Extensiveexperiments show that DomainAdaptor consistently outperforms thestate-of-the-art methods on four benchmarks. Furthermore, our method bringsmore remarkable improvement against existing methods on the few-data unseendomain. The code is available at https://github.com/koncle/DomainAdaptor.

DomainAdaptor: A Novel Approach to Test-time Adaptation