A precortical module for robust CNNs to light variations

2022/02/15 by R. Fioresi, Fioresi, R., J. Petkovic +1
Engineering · Neuroscience · #Artificial Intelligence (cs.AI) #CCD and CMOS Imaging Sensors #Computer Vision and Pattern Recognition (cs.CV) #Differential Geometry (math.DG) #FOS: Computer and information sciences #FOS: Mathematics #Neural dynamics and brain function #Visual perception and processing mechanisms

paper · pdf · doi:10.48550/arxiv.2202.07432

openalex publication_date 2022/02/15 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We present a simple mathematical model for the mammalian low visual pathway, taking into account its key elements: retina, lateral geniculate nucleus (LGN), primary visual cortex (V1). The analogies between the cortical level of the visual system and the structure of popular CNNs, used in image classification tasks, suggests the introduction of an additional preliminary convolutional module inspired to precortical neuronal circuits to improve robustness with respect to global light intensity and contrast variations in the input images. We validate our hypothesis on the popular databases MNIST, FashionMNIST and SVHN, obtaining significantly more robust CNNs with respect to these variations, once such extra module is added.

Related

• Explicitly Modeling Pre-Cortical Vision with a Neuro-Inspired Front-End Improves CNN Robustness
• Convolutional Neural Networks Exploiting Attributes of Biological Neurons
• Explicitly Modeling Subcortical Vision with a Neuro-Inspired Front-End Improves CNN Robustness
• Revealing Fine Structures of the Retinal Receptive Field by Deep Learning Networks
• Efficient Visual Coding: From Retina To V2