Dendritic Convolution for Noise Image Recognition

TL;DR

This paper introduces dendritic convolution, inspired by neuronal dendrites, to improve noise robustness in image recognition, significantly enhancing accuracy and detection performance in noisy conditions.

Contribution

It proposes a novel dendritic convolution that mimics biological neuron structures, integrating neighborhood interactions to better handle noise in image recognition tasks.

Findings

EfficientNet-B0 accuracy improved by 11.23% on noisy datasets

YOLOv8 mAP increased by 19.80% in noisy environments

Dendritic convolution outperforms traditional methods in complex noisy scenarios

Abstract

In real-world scenarios of image recognition, there exists substantial noise interference. Existing works primarily focus on methods such as adjusting networks or training strategies to address noisy image recognition, and the anti-noise performance has reached a bottleneck. However, little is known about the exploration of anti-interference solutions from a neuronal perspective.This paper proposes an anti-noise neuronal convolution. This convolution mimics the dendritic structure of neurons, integrates the neighborhood interaction computation logic of dendrites into the underlying design of convolutional operations, and simulates the XOR logic preprocessing function of biological dendrites through nonlinear interactions between input features, thereby fundamentally reconstructing the mathematical paradigm of feature extraction. Unlike traditional convolution where noise directly interferes with feature extraction and exerts a significant impact, DDC mitigates the influence of noise by focusing on the interaction of neighborhood information. Experimental results demonstrate that in image classification tasks (using YOLOv11-cls, VGG16, and EfficientNet-B0) and object detection tasks (using YOLOv11, YOLOv8, and YOLOv5), after replacing traditional convolution with the dendritic convolution, the accuracy of the EfficientNet-B0 model on noisy datasets is relatively improved by 11.23%, and the mean Average Precision (mAP) of YOLOv8 is increased by 19.80%. The consistency between the computation method of this convolution and the dendrites of biological neurons enables it to perform significantly better than traditional convolution in complex noisy environments.