# Neural Echos: Depthwise Convolutional Filters Replicate Biological Receptive Fields

Source: [Neural Echos: Depthwise Convolutional Filters Replicate Biological Receptive Fields](<https://www.sota2.com/research/paper/68fa71d71e209131cea5345d>)

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

Data updated: 2025-10-26T02:13:28.899Z

Authors: Zahra Babaiee, Peyman M. Kiasari, Daniela Rus, Radu Grosu

Published: 2024-01-18T18:06:22.000Z

## Abstract

In this study, we present evidence suggesting that depthwise convolutional kernels are effectively replicating the structural intricacies of the biological receptive fields observed in the mammalian retina. We provide analytics of trained kernels from various state-of-the-art models substantiating this evidence. Inspired by this intriguing discovery, we propose an initialization scheme that draws inspiration from the biological receptive fields. Experimental analysis of the ImageNet dataset with multiple CNN architectures featuring depthwise convolutions reveals a marked enhancement in the accuracy of the learned model when initialized with biologically derived weights. This underlies the potential for biologically inspired computational models to further our understanding of vision processing systems and to improve the efficacy of convolutional networks.

## 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/2401.10178>)

[PDF](<https://arxiv.org/pdf/2401.10178.pdf>)