Language selection

Government of Canada / Gouvernement du Canada

Search

Diversity is not a one-way street: pilot study on ethical interventions for racial bias in text-to-image systems

From National Research Council Canada

Download
  1. (PDF, 793 KiB)
AuthorSearch for: 1; Search for: 1; Search for: 1
Affiliation
  1. National Research Council of Canada. Digital Technologies
FunderSearch for: National Research Council of Canada. Digital Privacy and Security Program
FormatText, Article
Conference14th International Conference on Computational Creativity (ICCC'23), June 19-23, 2023, Waterloo, Ontario, Canada
Physical description5 p.
Abstract
Text-to-image generation models can reflect the underlying societal biases present in their training data. However, user-level interventions to encourage greater diversity in the output have been proposed. Here, we examine visually stereotypical output from three widely-used models: DALL-E 2, Mid-journey, and Stable Diffusion. Some of the prompts we consider (e.g., “a photo portrait of a lawyer”) result in an underrepresentation of darker-skinned individuals in the output, while other prompts (e.g., “a photo portrait of a felon”) result in over-representation of darker-skinned individuals. We show that existing linguistic interventions serve to correct for under-representation to some degree, but in fact amplify the bias in cases of over-representation for all three systems. Further work is needed to develop effective methods to promote equity, diversity, and inclusion in the output of image generation systems.
Publication date
PublisherInternational Conference on Computational Creativity
University of Waterloo
In
  • ICCC'23 (23 June 2023).
LanguageEnglish
Peer reviewedYes
IdentifierPaper 97
Export citationExport as RIS
Report a correctionReport a correction (opens in a new tab)
Record identifierade03101-9ec3-4e46-a5f9-2ebd5609ccdb
Record created2023-09-08
Record modified2025-11-03
Date modified: