Visual Illusions Also Deceive Convolutional Neural Networks: Analysis and Implications

Visual illusions allow researchers to devise and test new models of visual perception. Here we show that artificial neural networks trained for basic visual tasks in natural images are deceived by brightness and color illusions, having a response that is qualitatively very similar to the human achro...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Gomez-Villa, A, Martín, A, Vazquez-Corral, J, Bertalmío, M, Malo, J
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 03.12.2019
Subjects
Artificial neural networks
Illusions
Image contrast
Neural networks
Vision
Visual perception
Visual tasks
Online AccessGet full text

Cover

More Information
Summary:Visual illusions allow researchers to devise and test new models of visual perception. Here we show that artificial neural networks trained for basic visual tasks in natural images are deceived by brightness and color illusions, having a response that is qualitatively very similar to the human achromatic and chromatic contrast sensitivity functions, and consistent with natural image statistics. We also show that, while these artificial networks are deceived by illusions, their response might be significantly different to that of humans. Our results suggest that low-level illusions appear in any system that has to perform basic visual tasks in natural environments, in line with error minimization explanations of visual function, and they also imply a word of caution on using artificial networks to study human vision, as previously suggested in other contexts in the vision science literature.
ISSN:2331-8422