Book part In: cienciavitae

Contribution of V1 Receptive Field Properties to Corruption Robustness in CNNs

Barbulescu, Ruxandra; Tiago Marques; Arlindo L. Oliveira — 2024 — IOS Press

Key information

Authors:

Barbulescu, Ruxandra (Ruxandra Georgeta Barbulescu); Tiago Marques; Arlindo L. Oliveira

Published in

October 16, 2024

Abstract

<jats:p>Recently, it has been shown that simulating computations in early primate visual areas, up to the primary visual cortex (V1), at the front of convolutional neural networks (CNNs) leads to improvements in robustness to image corruptions. However, it remains unclear whether this improvement requires precisely matching the receptive field (RF) properties of V1 neurons or if some aspects are sufficient. Here, we explore this question by building several variants of a CNN model with a front-end modeling the primate V1 using a classical neuroscientific model, a Gabor Filter Bank (GFB) followed by simple- and complex- cell nonlinearities. Each model variant had varying levels of biological detail according to how the RF properties were sampled. The model variant sampling these parameters according to empirical biological distributions was considerably more robust to image corruptions than the variant sampling the parameters uniformly and independently (relative difference of 8.72%). However, a uniform variant capturing correlations between some GFB parameters obtained the same performance as the biological sampling variant. Our results show that it is not sufficient to approximate V1 with only the right class of function and parameter range, as it is also required to include the observed correlations between RF properties. However, it is not necessary to fully replicate the empirical distributions of V1 RF properties to obtain the desired improvement in robustness.</jats:p>

Publication details

Authors in the community:

Publisher

IOS Press

ISBN

9781643685489

Fields of Science and Technology (FOS)

electrical-engineering-electronic-engineering-information-engineering - Electrical engineering, electronic engineering, information engineering

Publication language (ISO code)

eng - English

Alternative identifier (URI)

http://dx.doi.org/10.3233/faia240546

Rights type:

Only metadata available