# Foveated Retinotopy Improves Classification and Localization in Convolutional Neural Networks

arXiv: https://arxiv.org/abs/2402.15480 · HTML: https://mlsanity.com/paper/2402.15480/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 67 references that are in the map.
- First posted on arXiv 23 Feb 2024.

## Builds on (most cited first, 19 of 19)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Spatial Transformer Networks](https://mlsanity.com/paper/1506.02025/) (2015)
- [Deep Image Prior](https://mlsanity.com/paper/1711.10925/) (2017)
- [Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks](https://mlsanity.com/paper/1910.01279/) (2019)
- [Adversarial Attacks on Neural Network Policies](https://mlsanity.com/paper/1702.02284/) (2017)
- [Learning SO(3) Equivariant Representations with Spherical CNNs](https://mlsanity.com/paper/1711.06721/) (2017)
- [AP-10K: A Benchmark for Animal Pose Estimation in the Wild](https://mlsanity.com/paper/2108.12617/) (2021)
- [Towards Biologically Plausible Deep Learning](https://mlsanity.com/paper/1502.04156/) (2015)
- [Opti-CAM: Optimizing saliency maps for interpretability](https://mlsanity.com/paper/2301.07002/) (2023)
- [CyCNN: A Rotation Invariant CNN using Polar Mapping and Cylindrical Convolution Layers](https://mlsanity.com/paper/2007.10588/) (2020)
- [End-to-end topographic networks as models of cortical map formation and human visual behaviour: moving beyond convolutions](https://mlsanity.com/paper/2308.09431/) (2023)
- [Human eye inspired log-polar pre-processing for neural networks](https://mlsanity.com/paper/1911.01141/) (2019)
- [Ultrafast Image Categorization in Biology and Neural Models](https://mlsanity.com/paper/2205.03635/) (2022)
- [Learning Robust Kernel Ensembles with Kernel Average Pooling](https://mlsanity.com/paper/2210.00062/) (2022)

## Abstract (arXiv)

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.