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

Domain Adaptation (DA) is always challenged by the spurious correlationbetween domain-invariant features (e.g., class identity) and domain-specificfeatures (e.g., environment) that does not generalize to the target domain.Unfortunately, even enriched with additional unsupervised target domains,existing Unsupervised DA (UDA) methods still suffer from it. This is becausethe source domain supervision only considers the target domain samples asauxiliary data (e.g., by pseudo-labeling), yet the inherent distribution in thetarget domain -- where the valuable de-correlation clues hide -- isdisregarded. We propose to make the U in UDA matter by giving equal status tothe two domains. Specifically, we learn an invariant classifier whoseprediction is simultaneously consistent with the labels in the source domainand clusters in the target domain, hence the spurious correlation inconsistentin the target domain is removed. We dub our approach "Invariant CONsistencylearning" (ICON). Extensive experiments show that ICON achieves thestate-of-the-art performance on the classic UDA benchmarks: Office-Home andVisDA-2017, and outperforms all the conventional methods on the challengingWILDS 2.0 benchmark. Codes are in https://github.com/yue-zhongqi/ICON.

Make the U in UDA Matter: Invariant Consistency Learning for Unsupervised Domain Adaptation