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 paper, we show that popular Generative Adversarial Networks (GANs)exacerbate biases along the axes of gender and skin tone when given a skeweddistribution of face-shots. While practitioners celebrate synthetic datageneration using GANs as an economical way to augment data for trainingdata-hungry machine learning models, it is unclear whether they recognize theperils of such techniques when applied to real world datasets biased alonglatent dimensions. Specifically, we show that (1) traditional GANs further skewthe distribution of a dataset consisting of engineering faculty headshots,generating minority modes less often and of worse quality and (2)image-to-image translation (conditional) GANs also exacerbate biases bylightening skin color of non-white faces and transforming female facialfeatures to be masculine when generating faces of engineering professors. Thus,our study is meant to serve as a cautionary tale.

Imperfect ImaGANation: Implications of GANs Exacerbating Biases on Facial Data Augmentation and Snapchat Selfie Lenses