2 citations · 2 across the 2 of their papers we have counts for
8 papers
Visual Illusions Also Deceive Convolutional Neural Networks: Analysis and Implications
A. Gomez-Villa, A. Martín, J. Vazquez-Corral +2
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…
Synthesizing Visual Illusions Using Generative Adversarial Networks
Alexander Gomez-Villa, Adrian Martín, Javier Vazquez-Corral +2
Visual illusions are a very useful tool for vision scientists, because they allow them to better probe the limits, thresholds and errors of the visual system. In this work we intro…
Cortical-inspired Wilson-Cowan-type equations for orientation-dependent contrast perception modelling
Marcelo Bertalmío, Luca Calatroni, Valentina Franceschi +2
We consider the evolution model proposed in [9, 6] to describe illusory contrast perception phenomena induced by surrounding orientations. Firstly, we highlight its analogies and d…
Visual Information flow in Wilson-Cowan networks
Alexander Gomez-Villa, Marcelo Bertalmío, Jesús Malo
In this work we study the communication efficiency of a psychophysically-tuned cascade of Wilson-Cowan and Divisive Normalization layers that simulate the retina-V1 pathway. This i…
Visual illusions via neural dynamics: Wilson-Cowan-type models and the efficient representation principle
Marcelo Bertalmío, Luca Calatroni, Valentina Franceschi +3
In this work we have aimed to reproduce supra-threshold perception phenomena, specifically visual illusions, with Wilson-Cowan-type models of neuronal dynamics. We have found that…
A cortical-inspired model for orientation-dependent contrast perception: a link with Wilson-Cowan equations
Marcelo Bertalmío, Luca Calatroni, Valentina Franceschi +2
We consider a differential model describing neuro-physiological contrast perception phenomena induced by surrounding orientations. The mathematical formulation relies on a cortical…