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/

Zendy Plus

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

Zendy Tools

Zendy Open

The performance of deep neural networks for image recognition tasks such aspredicting a smiling face is known to degrade with under-represented classes ofsensitive attributes. We address this problem by introducing fairness-awareregularization losses based on batch estimates of Demographic Parity, EqualizedOdds, and a novel Intersection-over-Union measure. The experiments performed onfacial and medical images from CelebA, UTKFace, and the SIIM-ISIC melanomaclassification challenge show the effectiveness of our proposed fairness lossesfor bias mitigation as they improve model fairness while maintaining highclassification performance. To the best of our knowledge, our work is the firstattempt to incorporate these types of losses in an end-to-end training schemefor mitigating biases of visual attribute predictors. Our code is available athttps://github.com/nish03/FVAP.

Enhancing Fairness of Visual Attribute Predictors