Colour vision has long fascinated scientists, who have sought to understand both the physiology of the mechanics of colour vision and the psychophysics of colour perception. We consider representations of colour in anatomically constrained convolutional deep neural networks. Following ideas from neuroscience, we classify cells in early layers into groups relating to their spectral and spatial functionality. We show the emergence of single and double opponent cells in our networks and characterise how the distribution of these cells changes under the constraint of a retinal bottleneck. Our experiments not only open up a new understanding of how deep networks process spatial and colour information, but also provide new tools to help understand the black box of deep learning. The code for all experiments is avaialable at \url{https://github.com/ecs-vlc/opponency}.
@article{arxiv.1910.11086,
title = {Spatial and Colour Opponency in Anatomically Constrained Deep Networks},
author = {Ethan Harris and Daniela Mihai and Jonathon Hare},
journal= {arXiv preprint arXiv:1910.11086},
year = {2019}
}