模仿神经元树突结构，提升图像识别在噪声下的准确率。
Dendritic Convolution for Noise Image Recognition
- 用树突结构设计新型卷积，通过邻域信息交互降噪。
- 在噪声数据上，EfficientNet-B0准确率提升11.23%，YOLOv8 mAP提升19.80%。
- 适合噪声环境下的图像分类与检测任务，生物启发性强。
现实场景中图像识别面临严重噪声干扰。现有方法多聚焦于调整网络或训练策略，抗噪性能已接近瓶颈。然而，从神经元视角探索抗干扰机制的研究仍较少。本文提出一种抗噪声神经元卷积（Dendritic Convolution, DDC），模仿神经元树突结构，将树突的邻域交互计算逻辑融入卷积底层设计，并通过输入特征间的非线性交互模拟生物树突的异或（XOR）预处理功能，从根本上重构特征提取的数学范式。与传统卷积中噪声直接干扰特征提取不同，DDC通过关注邻域信息交互来抑制噪声影响。实验表明，在图像分类（使用 YOLOv11-cls、VGG16、EfficientNet-B0）和目标检测（使用 YOLOv11、YOLOv8、YOLOv5）任务中，替换传统卷积后，EfficientNet-B0 在噪声数据集上的准确率相对提升 11.23%，YOLOv8 的平均精度均值（mAP）提升 19.80%。该卷积的计算方式与生物树突一致，使其在复杂噪声环境中表现显著优于传统卷积。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。