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

In this work, we present a framework to measure and mitigate intrinsic biaseswith respect to protected variables --such as gender-- in visual recognitiontasks. We show that trained models significantly amplify the association oftarget labels with gender beyond what one would expect from biased datasets.Surprisingly, we show that even when datasets are balanced such that each labelco-occurs equally with each gender, learned models amplify the associationbetween labels and gender, as much as if data had not been balanced! Tomitigate this, we adopt an adversarial approach to remove unwanted featurescorresponding to protected variables from intermediate representations in adeep neural network -- and provide a detailed analysis of its effectiveness.Experiments on two datasets: the COCO dataset (objects), and the imSitu dataset(actions), show reductions in gender bias amplification while maintaining mostof the accuracy of the original models.

Balanced Datasets Are Not Enough: Estimating and Mitigating Gender Bias in Deep Image Representations