Does AI See like Art Historians? Interpreting How Vision Language Models Recognize Artistic Style
This work addresses the interpretability of AI in art analysis for researchers and art historians, though it is incremental in applying existing methods to a new domain.
The paper investigates whether vision language models (VLMs) recognize artistic style similarly to art historians, finding that 73% of extracted concepts are coherent and 90% are relevant for style prediction, with irrelevant concepts sometimes explained by formal features like contrasts.
VLMs have become increasingly proficient at a range of computer vision tasks, such as visual question answering and object detection. This includes increasingly strong capabilities in the domain of art, from analyzing artwork to generation of art. In an interdisciplinary collaboration between computer scientists and art historians, we characterize the mechanisms underlying VLMs' ability to predict artistic style and assess the extent to which they align with the criteria art historians use to reason about artistic style. We employ a latent-space decomposition approach to identify concepts that drive art style prediction and conduct quantitative evaluations, causal analysis and assessment by art historians. Our findings indicate that 73% of the extracted concepts are judged by art historians to exhibit a coherent and semantically meaningful visual feature and 90% of concepts used to predict style of a given artwork were judged relevant. In cases where an irrelevant concept was used to successfully predict style, art historians identified possible reasons for its success; for example, the model might "understand" a concept in more formal terms, such as dark/light contrasts.