Dream Formulations and Deep Neural Networks: Humanistic Themes in the Iconology of the Machine-Learned Image

TL;DR

This paper explores the interpretability of deep learning in image recognition by comparing it with human perceptual theories, advocating for interdisciplinary collaboration and a revival of art historical methods to better understand machine-learned images.

Contribution

It reveals surprising parallels between machine learning image analysis and human perceptual theories, emphasizing the need for art historical insights in AI image interpretation.

Findings

Similarities between machine and human visual perception theories

Importance of art historical methods in AI image analysis

Call for interdisciplinary collaboration in AI interpretability

Abstract

This paper addresses the interpretability of deep learning-enabled image recognition processes in computer vision science in relation to theories in art history and cognitive psychology on the vision-related perceptual capabilities of humans. Examination of what is determinable about the machine-learned image in comparison to humanistic theories of visual perception, particularly in regard to art historian Erwin Panofsky's methodology for image analysis and psychologist Eleanor Rosch's theory of graded categorization according to prototypes, finds that there are surprising similarities between the two that suggest that researchers in the arts and the sciences would have much to benefit from closer collaborations. Utilizing the examples of Google's DeepDream and the Machine Learning and Perception Lab at Georgia Tech's Grad-CAM: Gradient-weighted Class Activation Mapping programs, this study suggests that a revival of art historical research in iconography and formalism in the age of AI is essential for shaping the future navigation and interpretation of all machine-learned images, given the rapid developments in image recognition technologies.