# Foveated Retinotopy Improves Classification and Localization in Convolutional Neural Networks

Source: [Foveated Retinotopy Improves Classification and Localization in Convolutional Neural Networks](<https://www.sota2.com/research/paper/68fa5f881e209131ce9eab73>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-12-17T05:01:50.819Z

Authors: Jean-Nicolas J\\'er\\'emie, Emmanuel Dauc\\'e, Laurent U Perrinet

Published: 2024-02-23T18:15:37.000Z

## Abstract

From falcons spotting preys to humans recognizing faces, rapid visual abilities depend on a foveated retinal organization which delivers high-acuity central vision while preserving low-resolution periphery. This organization is conserved along early visual pathways but remains underexplored in machine learning. Here we examine how embedding a foveated retinotopic transformation as a preprocessing layer impacts convolutional neural networks (CNNs) for image classification. By applying a log-polar mapping to off-the-shelf models and retraining them, we retain comparable accuracy while improving robustness to scale and rotation. We show that this architecture becomes highly sensitive to fixation-point shifts, and that this sensitivity yields a proxy for defining saliency maps that effectively facilitates object localization. Our results show that foveated retinotopy encodes prior geometric knowledge, offering a solution to visual-search and enhancing both classification and localization. These findings connect biological vision principles with artificial networks, pointing to new, robust and efficient directions for computer-vision systems.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2402.15480>)

[PDF](<https://arxiv.org/pdf/2402.15480.pdf>)
