Katalog Plus
Bibliothek der Frankfurt UAS
Bald neuer Katalog: sichern Sie sich schon vorab Ihre persönlichen Merklisten im Nutzerkonto: Anleitung.
Dieses Ergebnis aus BASE kann Gästen nicht angezeigt werden.  Login für vollen Zugriff.

Face the Facts: Using Face Averaging to Visualize Gender-by-Race Bias in Facial Analysis Algorithms

Title: Face the Facts: Using Face Averaging to Visualize Gender-by-Race Bias in Facial Analysis Algorithms
Authors: Owens, Kentrell; Freiburger, Erin; Hutchings, Ryan; Sim, Mattea; Hugenberg, Kurt; Roesner, Franziska; Kohno, Tadayoshi
Source: Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society; Vol. 7 No. 1 (2024): Proceedings of the Seventh AAAI/ACM Conference on AI, Ethics, and Society (AIES-24); 1101-1111 ; 3065-8365
Publisher Information: Association for the Advancement of Artificial Intelligence
Publication Year: 2024
Collection: Association for the Advancement of Artificial Intelligence: AAAI Publications
Description: We applied techniques from psychology --- typically used to visualize human bias --- to facial analysis systems, providing novel approaches for diagnosing and communicating algorithmic bias. First, we aggregated a diverse corpus of human facial images (N=1492) with self-identified gender and race. We tested four automated gender recognition (AGR) systems and found that some exhibited intersectional gender-by-race biases. Employing a technique developed by psychologists --- face averaging --- we created composite images to visualize these systems' outputs. For example, we visualized what an "average woman" looks like, according to a system's output. Second, we conducted two online experiments wherein participants judged the bias of hypothetical AGR systems. The first experiment involved participants (N=228) from a convenience sample. When depicting the same results in different formats, facial visualizations communicated bias to the same magnitude as statistics. In the second experiment with only Black participants (N=223), facial visualizations communicated bias significantly more than statistics, suggesting that face averages are meaningful for communicating algorithmic bias.
Document Type: article in journal/newspaper
File Description: application/pdf
Language: English
Relation: https://ojs.aaai.org/index.php/AIES/article/view/31707/33874; https://ojs.aaai.org/index.php/AIES/article/view/31707
DOI: 10.1609/aies.v7i1.31707
Availability: https://ojs.aaai.org/index.php/AIES/article/view/31707; https://doi.org/10.1609/aies.v7i1.31707
Rights: Copyright (c) 2024 Association for the Advancement of Artificial Intelligence
Accession Number: edsbas.5ACEC156
Database: BASE