TY - GEN
T1 - Analyzing demographic bias in artificially generated facial pictures
AU - Salminen, Joni
AU - Jung, Soon Gyo
AU - Chowdhury, Shammur
AU - Jansen, Bernard J.
N1 - Publisher Copyright:
© 2020 Owner/Author.
PY - 2020/4/25
Y1 - 2020/4/25
N2 - Artificial generation of facial images is increasingly popular, with machine learning achieving photo-realistic results. Yet, there is a concern that the generated images might not fairly represent all demographic groups. We use a state-of-the-art method to generate 10,000 facial images and find that the generated images are skewed towards young people, especially white women. We provide recommendations to reduce demographic bias in artificial image generation.
AB - Artificial generation of facial images is increasingly popular, with machine learning achieving photo-realistic results. Yet, there is a concern that the generated images might not fairly represent all demographic groups. We use a state-of-the-art method to generate 10,000 facial images and find that the generated images are skewed towards young people, especially white women. We provide recommendations to reduce demographic bias in artificial image generation.
UR - http://www.scopus.com/inward/record.url?scp=85090239557&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85090239557&partnerID=8YFLogxK
U2 - 10.1145/3334480.3382791
DO - 10.1145/3334480.3382791
M3 - Conference contribution
AN - SCOPUS:85090239557
T3 - Conference on Human Factors in Computing Systems - Proceedings
BT - CHI EA 2020 - Extended Abstracts of the 2020 CHI Conference on Human Factors in Computing Systems
PB - Association for Computing Machinery
T2 - 2020 ACM CHI Conference on Human Factors in Computing Systems, CHI EA 2020
Y2 - 25 April 2020 through 30 April 2020
ER -