Rxivist logo

Exploring Perceptual Illusions in Deep Neural Networks

By Emily J. Ward

Posted 02 Jul 2019
bioRxiv DOI: 10.1101/687905 (published DOI: 10.1167/19.10.34b)

Perceptual illusions—discrepancies between what exists externally and what we actually see—reveal a great deal about how the perceptual system functions. Rather than failures of perception, illusions expose automatic computations and biases in visual processing that help make better decisions from visual information to achieve our perceptual goals. Recognizing objects is one such perceptual goal that is shared between humans and certain Deep Convolutional Neural Networks, which can reach human-level performance. Do neural networks trained exclusively for object recognition “perceive” visual illusions, simply as a result of solving this one perceptual problem? Here, I showed four classic illusions to humans and a pre-trained neural network to see if the network exhibits similar perceptual biases. I found that deep neural networks trained exclusively for object recognition exhibit the Müller-Lyer illusion, but not other illusions. This result shows that some perceptual computations that are similar to humans’ may come “for free” in a system with perceptual goals similar to humans’.

Download data

  • Downloaded 507 times
  • Download rankings, all-time:
    • Site-wide: 28,440 out of 83,641
    • In neuroscience: 4,855 out of 14,924
  • Year to date:
    • Site-wide: 28,900 out of 83,641
  • Since beginning of last month:
    • Site-wide: 48,282 out of 83,641

Altmetric data

Downloads over time

Distribution of downloads per paper, site-wide


Sign up for the Rxivist weekly newsletter! (Click here for more details.)