Reducing Bias in AI-based Analysis of Visual Artworks

Zhuomin Zhang (1), Jia Li (1), David G. Stork (2), Elizabeth C. Mansfield (1), John Russell (1), Catherine Adams (1), and James Z. Wang (1)
(1) The Pennsylvania State University, University Park, PA 16802
(2) Independent Consultant, Portola Valley, CA 94028 USA

Empirical research in science and the humanities is vulnerable to bias which, by definition, implies incorrect or misleading findings. Artificial intelligence-based analysis of visual artworks is vulnerable to bias in ways specific to the domain. Works of art belong to a distinct cultural category that often prioritizes such characteristics as hand-craftsmanship, uniqueness, originality, and imaginative content; works of art are also responsive to diverse social and cultural contexts. Ascertaining which features of an artwork can be rightly ascribed to an objective “truth,” without which the concept of bias is not even relevant, is itself challenging. Incorporating expert knowledge into machine learning applications can help reduce bias in final estimates. We review several sources of bias that can occur across different stages of AI-based analysis, protocols and best practices for reducing bias, and approaches to measuring these biases. This systematic investigation of various types of bias can help researchers better understand bias, become aware of practical solutions, and ultimately cultivate the prudent adoption of AI-based approaches to artwork analysis.

Full Paper in Color
(PDF, 6.3MB)

On-line Info on the Research

Citation: Zhuomin Zhang, Jia Li, David G. Stork, Elizabeth C. Mansfield, John Russell, Catherine Adams and James Z. Wang, ``Reducing Bias in AI-based Analysis of Visual Artworks,'' IEEE BITS the Information Theory Magazine, Special Issue on Information Processing in Arts and Humanities, vol. 2, no. 1, pp. 36-48, 2022.

© 2022 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works, must be obtained from the IEEE.

Last Modified: December 10, 2022
© 2022