Emergent color categorization in a neural network trained for object recognition

Abstract
Data availability
Article and author information
Metrics

Abstract

Color is a prime example of categorical perception, yet it is unclear why and how color categories emerge. On the one hand, prelinguistic infants and several animals treat color categorically. On the other hand, recent modeling endeavors have successfully utilized communicative concepts as the driving force for color categories. Rather than modeling categories directly, we investigate the potential emergence of color categories as a result of acquiring visual skills. Specifically, we asked whether color is represented categorically in a convolutional neural network (CNN) trained to recognize objects in natural images. We systematically trained new output layers to the CNN for a color classification task and, probing novel colors, found borders that are largely invariant to the training colors. The border locations were confirmed using an evolutionary algorithm that relies on the principle of categorical perception. A psychophysical experiment on human observers, analogous to our primary CNN experiment, shows that the borders agree to a large degree with human category boundaries. These results provide evidence that the development of basic visual skills can contribute to the emergence of a categorical representation of color.

Data availability

The main analyses were computational and performed on ResNets from the models module of the torchvision package for python (see https://pytorch.org/vision/). Only Figure 4 is based on human data. Human data and source code for running the analysis and generating figures can be found at: https://github.com/vriesdejelmer/colorCategories/The code for the ipad experiment is available at:https://github.com/vriesdejelmer/ColorCoder/

Article and author information

Author details

Jelmer P de Vries

Experimental Psychology, University of Giessen, Giessen, Germany

Competing interests
The authors declare that no competing interests exist.
Arash Akbarinia

Experimental Psychology, University of Giessen, Giessen, Germany

Competing interests
The authors declare that no competing interests exist.

"This ORCID iD identifies the author of this article:" 0000-0002-4249-231X
Alban Flachot

Experimental Psychology, University of Giessen, Giessen, Germany

Competing interests
The authors declare that no competing interests exist.
Karl R Gegenfurtner

Experimental Psychology, University of Giessen, Giessen, Germany

For correspondence
gegenfurtner@uni-giessen.de

Competing interests
The authors declare that no competing interests exist.

"This ORCID iD identifies the author of this article:" 0000-0001-5390-0684

Funding

Deutsche Forschungsgemeinschaft (222641018 SFB TRR 135)

Jelmer P de Vries
Arash Akbarinia
Alban Flachot
Karl R Gegenfurtner

The funders had no role in study design, data collection and interpretation, or the decision to submit the work for publication.

Ethics

Human subjects: Informed consent was obtained from all observers prior to the experiment. All procedures were approved by the local ethics committee at Giessen University (LEK 2021-0033).

Copyright

This article is distributed under the terms of the Creative Commons Attribution License permitting unrestricted use and redistribution provided that the original author and source are credited.