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

Traditional empirical risk minimization (ERM) for semantic segmentation candisproportionately advantage or disadvantage certain target classes in favor ofan (unfair but) improved overall performance. Inspired by the recentlyintroduced tilted ERM (TERM), we propose tilted cross-entropy (TCE) loss andadapt it to the semantic segmentation setting to minimize performance disparityamong target classes and promote fairness. Through quantitative and qualitativeperformance analyses, we demonstrate that the proposed Stochastic TCE forsemantic segmentation can efficiently improve the low-performing classes ofCityscapes and ADE20k datasets trained with multi-class cross-entropy (MCCE),and also results in improved overall fairness.

Tilted Cross Entropy (TCE): Promoting Fairness in Semantic Segmentation