Corpus ID: 53783152

Convolutional Neural Networks Deceived by Visual Illusions

@article{Villa2018ConvolutionalNN,
  title={Convolutional Neural Networks Deceived by Visual Illusions},
  author={A. G. Villa and A. Mart{\'i}n and J. Vazquez-Corral and M. Bertalm{\'i}o},
  journal={ArXiv},
  year={2018},
  volume={abs/1811.10565}
}
  • A. G. Villa, A. Martín, +1 author M. Bertalmío
  • Published 2018
  • Computer Science
  • ArXiv
  • Visual illusions teach us that what we see is not always what it is represented in the physical world. [...] Key Result Our work opens a new bridge between human perception and CNNs: in order to obtain CNNs that better replicate human behaviour, we may need to start aiming for them to better replicate visual illusions.Expand Abstract
    2 Citations
    Spatial and Colour Opponency in Anatomically Constrained Deep Networks
    • 2
    • PDF
    Will We Ever Have Conscious Machines?
    • PDF

    References

    SHOWING 1-10 OF 23 REFERENCES
    Optical Illusions Images Dataset
    • 7
    • PDF
    Illusory Motion Reproduced by Deep Neural Networks Trained for Prediction
    • 36
    • PDF
    Natural Image Denoising with Convolutional Networks
    • 605
    • PDF
    Noise masking of White's illusion exposes the weakness of current spatial filtering models of lightness perception.
    • 57
    • PDF
    Derivatives and inverse of cascaded linear+nonlinear neural models
    • 19
    • PDF
    Lightness Perception and Lightness Illusions
    • 397
    • PDF
    Explaining Lightness Illusions
    • 81
    Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
    • 2,338
    • PDF
    Illuminant estimation for color constancy: why spatial-domain methods work and the role of the color distribution.
    • 174
    • PDF
    Denoising and contrast constancy
    • 7