Back to articles
Volume: 24 | Article ID: art00038
Color spaces emerging from deep convolutional networks
  DOI :  10.2352/ISSN.2169-2629.2017.32.225  Published OnlineNovember 2016

Defining color spaces that provide a good encoding of spatio-chromatic properties of color surfaces is an open problem in color science [8, 22]. Related to this, in computer vision the fusion of color with local image features has been studied and evaluated [16]. In human vision research, the cells which are selective to specific color hues along the visual pathway are also a focus of attention [7, 14]. In line with these research aims, in this paper we study how color is encoded in a deep Convolutional Neural Network (CNN) that has been trained on more than one million natural images for object recognition. These convolutional nets achieve impressive performance in computer vision, and rival the representations in human brain. In this paper we explore how color is represented in a CNN architecture that can give some intuition about efficient spatio-chromatic representations. In convolutional layers the activation of a neuron is related to a spatial filter, that combines spatio-chromatic representations. We use an inverted version of it to explore the properties. Using a series of unsupervised methods we classify different type of neurons depending on the color axes they define and we propose an index of color-selectivity of a neuron. We estimate the main color axes that emerge from this trained net and we prove that colorselectivity of neurons decreases from early to deeper layers.

Subject Areas :
Views 13
Downloads 2
 articleview.views 13
 articleview.downloads 2
  Cite this article 

Ivet Rafegas, Maria Vanrell, "Color spaces emerging from deep convolutional networksin Proc. IS&T 24th Color and Imaging Conf. ,  2016,

 Copy citation
  Copyright statement 
Copyright © Society for Imaging Science and Technology 2016
Color and Imaging Conference
color imaging conf
Society for Imaging Science and Technology