No CrossRef data available.
Article contents
A deep new look at color
Published online by Cambridge University Press: 06 December 2023
Abstract
Bowers et al. counter deep neural networks (DNNs) as good models of human visual perception. From our color perspective we feel their view is based on three misconceptions: A misrepresentation of the state-of-the-art of color perception; the type of model required to move the field forward; and the attribution of shortcomings to DNN research that are already being resolved.
- Type
- Open Peer Commentary
- Information
- Copyright
- Copyright © The Author(s), 2023. Published by Cambridge University Press
References
Biederman, I. (1987). Recognition-by-components: A theory of human image understanding. Psychological Review, 94(2), 115–147. https://doi.org/10.4324/9781351156288-24CrossRefGoogle ScholarPubMed
Conway, B. R. (2018). The organization and operation of inferior temporal cortex. Annual Review of Vision Science, 4(1), 381–402. https://doi.org/10.1146/annurev-vision-091517-034202CrossRefGoogle ScholarPubMed
de Vries, J. P., Akbarinia, A., Flachot, A., & Gegenfurtner, K. R. (2022). Emergent color categorization in a neural network trained for object recognition. eLife, 11, e76472. https://doi.org/10.7554/eLife.76472CrossRefGoogle Scholar
Flachot, A., Akbarinia, A., Schütt, H. H., Fleming, R. W., Wichmann, F. A., & Gegenfurtner, K. R. (2022). Deep neural models for color classification and color constancy. Journal of Vision, 22(4), 1–24. https://doi.org/10.1167/jov.22.4.17CrossRefGoogle ScholarPubMed
Flachot, A., & Gegenfurtner, K. R. (2018). Processing of chromatic information in a deep convolutional neural network. Journal of the Optical Society of America A, 35(4), B334. https://doi.org/10.1364/josaa.35.00b334CrossRefGoogle ScholarPubMed
Flachot, A., & Gegenfurtner, K. R. (2021). Color for object recognition: Hue and chroma sensitivity in the deep features of convolutional neural networks. Vision Research, 182, 89–100. https://doi.org/10.1016/j.visres.2020.09.010CrossRefGoogle ScholarPubMed
Garg, A. K., Li, P., Rashid, M. S., & Callaway, E. M. (2019). Color and orientation are jointly coded and spatially organized in primate primary visual cortex. Science (New York, N.Y.), 364(6447), 1275–1279. https://doi.org/10.1126/science.aaw5868CrossRefGoogle ScholarPubMed
Gegenfurtner, K. R. (2003). Cortical mechanisms of colour vision. Nature Reviews Neuroscience, 4(7), 563–572. https://doi.org/10.1038/nrn1138CrossRefGoogle ScholarPubMed
Gegenfurtner, K. R., & Kiper, D. C. (2003). Annual review of neuroscience, 26, 181–206. https://doi.org/10.1146/annurev.neuro.26.041002.131116CrossRefGoogle Scholar
Hansen, T., & Gegenfurtner, K. R. (2009). Independence of color and luminance edges in natural scenes. Visual Neuroscience, 26(1), 35–49. https://doi.org/10.1017/S0952523808080796CrossRefGoogle ScholarPubMed
Hansen, T., & Gegenfurtner, K. R. (2017). Color contributes to object-contour perception in natural scenes. Journal of Vision, 17(3), 1–19. https://doi.org/10.1167/17.3.14CrossRefGoogle ScholarPubMed
Krakauer, J. W., Ghazanfar, A. A., Gomez-Marin, A., MacIver, M. A., & Poeppel, D. (2017). Neuroscience needs behavior: Correcting a reductionist bias. Neuron, 93(3), 480–490. https://doi.org/10.1016/j.neuron.2016.12.041CrossRefGoogle ScholarPubMed
Livingstone, M. S., & Hubel, D. H. (1987). Psychophysical evidence for separate channels for the perception of form, color, movement, and depth. Journal of Neuroscience, 7(11), 3416–3468. https://doi.org/10.1523/jneurosci.07-11-03416.1987CrossRefGoogle ScholarPubMed
Ponting, S., Morimoto, T., & Smithson, H. (2023). Modelling surface color discrimination under different lighting environments using image chromatic statistics and convolutional neural networks. Journal of the Optical Society of America A, 40(3), A149–A159. https://doi.org/10.1364/josaa.479986CrossRefGoogle ScholarPubMed
Rafegas, I., & Vanrell, M. (2018). Color encoding in biologically-inspired convolutional neural networks. Vision Research, 151, 7–17. https://doi.org/10.1016/j.visres.2018.03.010CrossRefGoogle ScholarPubMed
Rafegas, I., Vanrell, M., Alexandre, L. A., & Arias, G. (2020). Understanding trained CNNs by indexing neuron selectivity. Pattern Recognition Letters, 136, 318–325.CrossRefGoogle Scholar
Shamay-Tsoory, S. G., & Mendelsohn, A. (2019). Real-life neuroscience: An ecological approach to brain and behavior research. Perspectives on Psychological Science, 14(5), 841–859. https://doi.org/10.1177/1745691619856350CrossRefGoogle ScholarPubMed
Shapley, R., & Hawken, M. J. (2011). Color in the cortex: Single- and double-opponent cells. Vision Research, 51(7), 701–717. https://doi.org/10.1016/j.visres.2011.02.012CrossRefGoogle ScholarPubMed
Siuda-Krzywicka, K., & Bartolomeo, P. (2020). What cognitive neurology teaches us about our experience of color. Neuroscientist, 26(3), 252–265. https://doi.org/10.1177/1073858419882621CrossRefGoogle ScholarPubMed
Witzel, C., & Gegenfurtner, K. R. (2018). Color perception: Objects, constancy, and categories. Annual Review of Vision Science, 4, 475–499.CrossRefGoogle ScholarPubMed
Wright, A. A., & Cumming, W. W. (1971). Color-naming functions for the pigeon. Journal of the Experimental Analysis of Behavior, 15(1), 7–17.CrossRefGoogle ScholarPubMed
Target article
Deep problems with neural network models of human vision
Related commentaries (29)
Explananda and explanantia in deep neural network models of neurological network functions
A deep new look at color
Beyond the limitations of any imaginable mechanism: Large language models and psycholinguistics
Comprehensive assessment methods are key to progress in deep learning
Deep neural networks are not a single hypothesis but a language for expressing computational hypotheses
Even deeper problems with neural network models of language
Fixing the problems of deep neural networks will require better training data and learning algorithms
For deep networks, the whole equals the sum of the parts
For human-like models, train on human-like tasks
Going after the bigger picture: Using high-capacity models to understand mind and brain
Implications of capacity-limited, generative models for human vision
Let's move forward: Image-computable models and a common model evaluation scheme are prerequisites for a scientific understanding of human vision
Modelling human vision needs to account for subjective experience
Models of vision need some action
My pet pig won't fly and I want a refund
Neither hype nor gloom do DNNs justice
Neural networks need real-world behavior
Neural networks, AI, and the goals of modeling
Perceptual learning in humans: An active, top-down-guided process
Psychophysics may be the game-changer for deep neural networks (DNNs) to imitate the human vision
Statistical prediction alone cannot identify good models of behavior
The model-resistant richness of human visual experience
The scientific value of explanation and prediction
There is a fundamental, unbridgeable gap between DNNs and the visual cortex
Thinking beyond the ventral stream: Comment on Bowers et al.
Using DNNs to understand the primate vision: A shortcut or a distraction?
Where do the hypotheses come from? Data-driven learning in science and the brain
Why psychologists should embrace rather than abandon DNNs
You can't play 20 questions with nature and win redux
Author response
Clarifying status of DNNs as models of human vision