信息与控制2025，Vol.54Issue(6)：801-811,11.DOI:10.13976/j.cnki.xk.2024.4742
基于多尺度冗余特征的轻量化特征融合模块
Lightweight Feature Fusion Module Based on Multi-scale Redundant Features
摘要
Abstract
Convolutional neural networks perform outstandingly in computer vision tasks but often face long inference times,large parameter sizes,and large floating point of operations.We identify multi-scale feature redundancy in hierarchical convolutional neural networks and develop an effi-cient multi-scale feature fusion module,the mixed and difference enhancement module.The mix block merges redundant features and enhances feature learning by leveraging this redundancy.The difference enhancement block focuses on the differences between features,optimizing the module's representation ability in small-sample tasks.We integrate the mixed and difference enhancement module into various network models for different tasks.Experiment results demonstrate that the mixed and difference enhancement module,as a plug-and-play component,reduces the parameter sizes,floating point of operations,and inference times without complex adjustments to the existing model.The mixed and difference enhancement module also exhibits superior feature representation abilities and significantly improves performance.关键词
特征融合/轻量化模块/卷积神经网络Key words
feature fusion/lightweight model/convolutional neural network分类
信息技术与安全科学引用本文复制引用
汪正华,王予,倪梓豪,杨永良..基于多尺度冗余特征的轻量化特征融合模块[J].信息与控制,2025,54(6):801-811,11.基金项目
国家自然科学基金项目(62273338) （62273338）
