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} }
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
Figures, Tables, and Topics from this paper
Paper Mentions
2 Citations
Spatial and Colour Opponency in Anatomically Constrained Deep Networks
- Computer Science, Mathematics
- ArXiv
- 2019
- 2
- PDF
Will We Ever Have Conscious Machines?
- Medicine, Computer Science
- Frontiers in Computational Neuroscience
- 2020
- PDF
References
SHOWING 1-10 OF 23 REFERENCES
Illusory Motion Reproduced by Deep Neural Networks Trained for Prediction
- Psychology, Medicine
- Front. Psychol.
- 2018
- 36
- PDF
Noise masking of White's illusion exposes the weakness of current spatial filtering models of lightness perception.
- Psychology, Medicine
- Journal of vision
- 2015
- 57
- PDF
Derivatives and inverse of cascaded linear+nonlinear neural models
- Medicine, Mathematics
- PloS one
- 2018
- 19
- PDF
Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
- Computer Science, Medicine
- IEEE Transactions on Image Processing
- 2017
- 2,338
- PDF
Illuminant estimation for color constancy: why spatial-domain methods work and the role of the color distribution.
- Computer Science, Medicine
- Journal of the Optical Society of America. A, Optics, image science, and vision
- 2014
- 174
- PDF