A Hypothesis for the Aesthetic Appreciation in Neural Networks
This addresses the problem of interpreting aesthetic judgments in AI for researchers in computer vision and AI ethics, but it appears incremental as it builds on existing concepts without major breakthroughs.
The paper tackles the problem of understanding aesthetic appreciation in neural networks by proposing that aesthetic images strengthen salient concepts and discard inessential ones, and finds that revised images based on this hypothesis are more aesthetic to some extent.
This paper proposes a hypothesis for the aesthetic appreciation that aesthetic images make a neural network strengthen salient concepts and discard inessential concepts. In order to verify this hypothesis, we use multi-variate interactions to represent salient concepts and inessential concepts contained in images. Furthermore, we design a set of operations to revise images towards more beautiful ones. In experiments, we find that the revised images are more aesthetic than the original ones to some extent.