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 generalization (DG) is proposed to deal with the issue of domainshift, which occurs when statistical differences exist between source andtarget domains. However, most current methods do not account for a commonrealistic scenario where the source and target domains have different classes.To overcome this deficiency, open set domain generalization (OSDG) then emergesas a more practical setting to recognize unseen classes in unseen domains. Anintuitive approach is to use multiple one-vs-all classifiers to define decisionboundaries for each class and reject the outliers as unknown. However, thesignificant class imbalance between positive and negative samples often causesthe boundaries biased towards positive ones, resulting in misclassification forknown samples in the unseen target domain. In this paper, we propose a novelmeta-learning-based framework called dualistic MEta-learning with jointDomaIn-Class matching (MEDIC), which considers gradient matching towardsinter-domain and inter-class splits simultaneously to find a generalizableboundary balanced for all tasks. Experimental results demonstrate that MEDICnot only outperforms previous methods in open set scenarios, but also maintainscompetitive close set generalization ability at the same time. Our code isavailable at https://github.com/zzwdx/MEDIC.

Generalizable Decision Boundaries: Dualistic Meta-Learning for Open Set Domain Generalization