2 citations · 2 across the 2 of their papers we have counts for
5 papers · 1 filter
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…
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…
Convolutional Neural Networks Deceived by Visual Illusions
Alexander Gomez-Villa, Adrián Martín, Javier Vazquez-Corral +1
Visual illusions teach us that what we see is not always what it is represented in the physical world. Its special nature make them a fascinating tool to test and validate any new…