2021/09/16 by Romuald A. Janik, Janik, Romuald A. · 1 citation
Neuroscience · #Aesthetic Perception and Analysis #Computer Vision and Pattern Recognition (cs.CV) #FOS: Biological sciences #FOS: Computer and information sciences #FOS: Electrical engineering #Image and Video Processing (eess.IV) #Neurons and Cognition (q-bio.NC) #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2109.08103
openalex publication_date 2021/09/16 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
We analyze the spaces of images encoded by generative neural networks of the BigGAN architecture. We find that generic multiplicative perturbations of neural network parameters away from the photo-realistic point often lead to networks generating images which appear as "artistic renditions" of the corresponding objects. This demonstrates an emergence of aesthetic properties directly from the structure of the photo-realistic visual environment as encoded in its neural network parametrization. Moreover, modifying a deep semantic part of the neural network leads to the appearance of symbolic visual representations. None of the considered networks had any access to images of human-made art.