Retinotopy in CNN's implements Efficient Visual Search

Abstract

While foveated vision, a trait shared by many animals including humans, is a major contributor to biological visual performance, it has been underutilized in machine learning applications. This study investigates whether retinotopic mapping, a critical component of foveated vision, can enhance image categorization and localization performance when integrated into deep convolutional neural networks (CNN’s). Retinotopic mapping was used to transform the inputs of standard off-the-shelf CNN’s which were then retrained on the Imagenet task. Surprisingly, the networks with retinotopically-mapped inputs achieved a comparable performance in classification. Furthermore, the networks demonstrated improved classification localization when the foveated center of the transform was moved on the whole image. This replicates a crucial ability of the human visual system that is absent in typical CNN’s. These findings suggest that retinotopic mapping may be fundamental to significant preattentive visual processes, in particular the retinotopic version seems to be the best option when applying one of these networks to a visual search task.

Jean-Nicolas Jérémie

Phd candidate in Computational Neuroscience

During my PhD, I am focusing on ultra-fast processing in event-based neural networks.

Emmanuel Daucé

Laurent U Perrinet

Researcher in Computational Neuroscience

My research interests include Machine Learning and computational neuroscience applied to Vision.