佛山科学技术学院学报（自然科学版）2025，Vol.43Issue(5)：32-38,7.
深度卷积神经网络中的共享特征层设计与优化
Design and optimization of shared feature layer in deep convolutional neural networks
张仁冬 1叶树林 1胡宏升1
作者信息
- 1. 佛山大学机电工程与自动化学院,广东 佛山 528225
- 折叠
摘要
Abstract
As the depth of neural networks increases,the problems of the gradient vanishing and the gradient explosion become increasingly prominent.Meanwhile,improving feature reuse rate and reducing computational complexity have emerged as key challenges.This paper proposes a feature extraction network based on shared feature layer,and designs a dynamic iterative update mechanism.This mechanism integrates the output features of all previous layers and those of the current layer,and combines batch channel normalization to improve feature reuse efficiency.The shared feature layer is connected to the backbone network via residual connections,which enables effective feature updating and maintains gradient stability in the process of backpropagation.The experimental results show that the Top-1 error rate of SFLN-152 on ImageNet dataset is 19.00%,which is 11.34%and 5%lower than that of ResNet-152 and DPN-131,respectively.The classification error rates on the CIFAR-10 and CIFAR-100 datasets are 4.77%and 19.85%.关键词
特征提取/梯度稳定/批量通道归一化/共享特征层Key words
feature extraction/gradient stability/batch-channel normalization/shared feature layer分类
信息技术与安全科学引用本文复制引用
张仁冬,叶树林,胡宏升..深度卷积神经网络中的共享特征层设计与优化[J].佛山科学技术学院学报（自然科学版）,2025,43(5):32-38,7.
