Reducing Bias in AI-Based Analysis of Visual Artworks
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.
Related Articles
Image Processing and the Analysis of Paintings—The Case of Serbian Baroque Icons
Technical studies of paintings are based on many analytical techniques that complement art historical studies. Understanding the processes that happen with the aging of the paint is very important for conservators. The paint layer cracks and lifts, the materials discolor and new layers are added over time, slowly changing the appearance of the artwork. Crack patterns in the paint layer can be used in the study of the composition of the paint layer as well as its conservation history...
(Re)discovering Laws of Music Theory Using Information Lattice Learning
Information lattice learning (ILL) is a novel framework for knowledge discovery based on group-theoretic and information-theoretic foundations, which can red...
Revealing and Reconstructing Hidden or Lost Features in Art Investigation
In recent decades, cultural heritage research—and in particular art investigation—has been undergoing a digital revolution. This is due both to improvements ...
