A deep convolutional neural network trained for lightness constancy is susceptible to lightness illusions
Journal of Vision · 25.03.2026 · 26 (3) · 14
DOI: 10.1167/jov.26.3.14 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Vision, erschienen am 25.03.2026. Verfasst von Jaykishan Patel und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Psychology and Centre for Vision Research, York University, Toronto, Ontario, Canada. Hauptthemen laut MEDLINE: Convolutional Neural Networks, Optical Illusions, Lighting, Contrast Sensitivity. Die Arbeit nennt 61 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
Kein Abstract verfügbar.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Psychology and Centre for Vision Research, York University, Toronto, Ontario, Canada.
- jay96@my.yorku.ca.
- flachot.alban@gmail.com.
- Department of Computer Science, Universitat Autònoma de Barcelona, Barcelona, Spain.
- Computer Vision Center, Barcelona, Spain.
- jvazquez@cvc.uab.cat.
Zitieren
APA
Patel, J., Flachot, A., Vazquez-Corral, J., Brainard, D. H., Wallis, T. S. A., Brubaker, M. A., & Murray, R. F. (2026). A deep convolutional neural network trained for lightness constancy is susceptible to lightness illusions. Journal of Vision, 26(3), 14. https://doi.org/10.1167/jov.26.3.14
Vancouver
Patel J, Flachot A, Vazquez-Corral J, Brainard DH, Wallis TSA, Brubaker MA, et al. A deep convolutional neural network trained for lightness constancy is susceptible to lightness illusions. Journal of Vision. 2026;26(3):14. doi:10.1167/jov.26.3.14
BibTeX
@article{Patel2026,
author = {Patel, Jaykishan and Flachot, Alban and Vazquez-Corral, Javier and Brainard, David H and Wallis, Thomas S A and Brubaker, Marcus A and Murray, Richard F},
title = {A deep convolutional neural network trained for lightness constancy is susceptible to lightness illusions},
journal = {Journal of Vision},
year = {2026},
volume = {26},
number = {3},
pages = {14},
doi = {10.1167/jov.26.3.14}
}
EUVIMED