信息与控制2025，Vol.54Issue(2)：321-335,352,16.DOI:10.13976/j.cnki.xk.2025.4335
一种轻量级空间位置注意力模块及其在图像分类网络中的应用
Lightweight Spatial Location Attention Module and Its Application to Image Classification Networks
摘要
Abstract
A lightweight spatial location attention module(SLAM)is proposed to address the shortcom-ings of previous attention methods that often overlook the critical role of spatial location information in cross-dimensional interactions.This module calculates the location information attention weights of the input feature map across horizontal,vertical,and channel directions through three branch structures,which results in the aggregation of features along the three spatial directions for adaptive adjustment of spatial and positional information attention weights in the feature map.Based on this module,ResNet18,ResNet50,and MobileNetV2 networks are improved,and a large number of experiments are conducted for image classification tasks.The results show that SLAM considerably improves model performance,outperforming other attention methods.In particular,on the classification tasks of ImageNet-1K and Stanford-Cars datasets,the Top-1 accuracy of the ResNet18,ResNet50,and MobileNetV2 networks improved by SLAM is the highest,increasing by 2.62%and 2.4%,re-spectively.In the scrap steel rating task,the YOLOv5s and YOLOv8s networks enhanced with SLAM show improvements across four indicators:recall,F1 Score,mAP0.5:0.95,and mAP0.5.These results surpass the performance of the networks improved with convolutional block attention module and coordinate attention.关键词
注意力机制/空间位置信息/图像分类Key words
attention mechanism/spatial location information/image classification分类
计算机与自动化引用本文复制引用
许云峰,刘畅达,梅卫,徐振峰,张妍..一种轻量级空间位置注意力模块及其在图像分类网络中的应用[J].信息与控制,2025,54(2):321-335,352,16.基金项目
河北省科技厅科技研发平台建设专项(23561007D) （23561007D）
河北省重点研发计划项目(21373802D) （21373802D）
