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

Although significant progress has been made in face recognition, demographicbias still exists in face recognition systems. For instance, it usually happensthat the face recognition performance for a certain demographic group is lowerthan the others. In this paper, we propose MixFairFace framework to improve thefairness in face recognition models. First of all, we argue that the commonlyused attribute-based fairness metric is not appropriate for face recognition. Aface recognition system can only be considered fair while every person has aclose performance. Hence, we propose a new evaluation protocol to fairlyevaluate the fairness performance of different approaches. Different fromprevious approaches that require sensitive attribute labels such as race andgender for reducing the demographic bias, we aim at addressing the identitybias in face representation, i.e., the performance inconsistency betweendifferent identities, without the need for sensitive attribute labels. To thisend, we propose MixFair Adapter to determine and reduce the identity bias oftraining samples. Our extensive experiments demonstrate that our MixFairFaceapproach achieves state-of-the-art fairness performance on all benchmarkdatasets.

MixFairFace: Towards Ultimate Fairness via MixFair Adapter in Face Recognition