EUVIMEDEUVIMED entdecken
Crossref

Task-dependent color representation in convolutional neural networks

Jenny M Bosten, S Angela Diyalagoda

Journal of the Optical Society of America A · 2025

DOI: 10.1364/josaa.546067 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of the Optical Society of America A, 2025. Verfasst von Jenny M Bosten und 1 weiteren Autor:innen. Hauptthemen laut MEDLINE: Color Perception, Neural Networks, Computer. Die Arbeit nennt 50 Literaturangaben. Gefördert von: European Research Council.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Convolutional neural networks (CNNs) trained for image categorization are known to have color-selective units that are tuned to particular colors. Analogously to the analysis of color representations in humans using brain imaging data, the representation of color within layers of a trained network can be characterized by constructing representational dissimilarity matrices (RDMs) and by using multidimensional scaling (MDS) to visualize geometric representational color spaces. Human color representations show flexibility dependent on the task. We trained CNNs on a set of simple chromatic stimuli but varied the “task” to require either color categorization, an analog of a color appearance rating, or luminance or spatial judgments that may not require color at all. We found that color representations within trained networks differed reliably and distinctively between task conditions, and that structured representations developed for color-relevant training conditions that were appropriate to the task. Color representations for different task conditions diverged through network layers toward the output layer, but they were significantly different even for layer 2 near the input layer. The variance between network instances was lowest for color-relevant tasks. For two of the tasks initially assumed to be “color-irrelevant,” reliable and distinctive color representations developed. For these tasks requiring luminance or spatial judgments, color must provide a useful cue even though it is not required in the network output. These results or similar models may be used to generate hypotheses for how color representations in the human brain vary with task (whether tasks obviously require color or not), which could be tested using neuroimaging.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Color PerceptionNeural Networks, ComputerHumansColorConvolutional Neural Networks

Förderung

  • European Research Council

Zitieren

APA

Bosten, J. M., & Diyalagoda, S. A. (2025). Task-dependent color representation in convolutional neural networks. Journal of the Optical Society of America A. https://doi.org/10.1364/josaa.546067

Vancouver

Bosten JM, Diyalagoda SA. Task-dependent color representation in convolutional neural networks. Journal of the Optical Society of America A. 2025. doi:10.1364/josaa.546067

BibTeX
@article{Bosten2025,
  author = {Bosten, Jenny M and Diyalagoda, S Angela},
  title = {Task-dependent color representation in convolutional neural networks},
  journal = {Journal of the Optical Society of America A},
  year = {2025},
  doi = {10.1364/josaa.546067}
}
Kostenlos starten →