用于图像分类的深度卷积神经网络中的空间分割注意力模块

王方; 乔瑞萍

doi:10.7652/xjtuxb202309019

您当前的位置：

首页 >

文章列表页 >

用于图像分类的深度卷积神经网络中的空间分割注意力模块

—————————————————————— | 更新时间：2025-07-09

- 用于图像分类的深度卷积神经网络中的空间分割注意力模块
- SPAM: Spatially Partitioned Attention Module in Deep Convolutional Neural Networks for Image Classification
- 西安交通大学学报 2023年57卷第9期页码：185-192
- 作者机构：
  
  西安交通大学信息与通信工程学院,西安,710049
- 作者简介：
  
  : 2023-02-14。作者简介: 王方(1998—),男,硕士生
  乔瑞萍(通信作者),女,副教授,硕士生导师。基金项目: 陕西省重点研发计划资助项目(2020GY-074)。
- 基金信息：
  
  : 2023-02-14。作者简介: 王方(1998—),男,硕士生;乔瑞萍(通信作者),女,副教授,硕士生导师。基金项目: 陕西省重点研发计划资助项目(2020GY-074)。
- DOI：10.7652/xjtuxb202309019
  中图分类号： TP391.4
- 网络首发：2023-09-10，
  
  纸质出版：2023
- 稿件说明：
移动端阅览
王方, 乔瑞萍. 用于图像分类的深度卷积神经网络中的空间分割注意力模块[J]. 西安交通大学学报, 2023,57(9):185-192.

WANG Fang, QIAO Ruiping. SPAM: Spatially Partitioned Attention Module in Deep Convolutional Neural Networks for Image Classification[J]. 2023, 57(9): 185-192.
王方, 乔瑞萍. 用于图像分类的深度卷积神经网络中的空间分割注意力模块[J]. 西安交通大学学报, 2023,57(9):185-192. DOI： 10.7652/xjtuxb202309019.

WANG Fang, QIAO Ruiping. SPAM: Spatially Partitioned Attention Module in Deep Convolutional Neural Networks for Image Classification[J]. 2023, 57(9): 185-192. DOI： 10.7652/xjtuxb202309019.

摘要

针对现有注意力机制常采用融合或压缩的方式来获取所需信息

会导致空间或通道维度损失的信息过多的问题

提出了一种有效的轻量级注意力模块SPAM

它可以在不经过通道融合或压缩的情况下获取注意力。对于输入的中间特征图

SPAM首先会自适应地采用平均池化和最大池化来进行特征提取; 采用空间上局部的块特征代替点特征以减少计算量

并利用实例标准化(IN)层与深层卷积来捕获全局空间注意力; 通道维度信息的重建通过分组卷积来完成; 最终使用插值操作获得整体注意力

对输入特征图进行加权。SPAM可以方便地嵌入到各种主流卷积神经网络架构中

只需增加微量参数和计算量

就可以显著提高网络性能。为了证明SPAM的有效性

在ImageNet-1K、CIFAR-100和Food-101图像分类数据集上进行了大量实验

并使用Grad-CAM可视化了网络的关注区域。实验结果表明

在ImageNet-1K、CIFAR-100和Food-101数据集上

SPAM分别将基线网络的准确率最多提高了约1.08%、2.46%和1.09%。研究结果表明

嵌入SPAM的网络的性能都有较大提升; 且相较于其他常用的轻量级注意力机制

SPAM的效果始终更好; SPAM使网络更关注目标对象所在区域

确切提高了网络的表达能力。

Abstract

Existing attention mechanisms often use fusion or compression to obtain the required information

but this leads to a large quantity of information lost in the spatial or channel dimension. In order to solve this problem

the Spatially Partitioned Attention Module(SPAM)

a really effective and lightweight attention module that can help obtain attention without channel fusion or compression

was proposed in the paper. For the input intermediate feature map

the SPAM first adaptively used average pooling and maximum pooling features for feature extraction

replaced the point feature with the local block feature in space to reduce the amount of calculation and used the IN layer and depthwise convolution to capture global spatial attention. Meanwhile

the reconstruction of channel dimension information was directly completed by group convolution. Finally

the interpolation operation was used to obtain overall attention and weight the input feature map. Notably

the SPAM can be easily embedded in various mainstream CNN architectures

and network performance can be significantly improved by increasing a few microparameters and calculations. To demonstrate the effectiveness of the SPAM

numerous experiments were conducted on the ImageNet-1K

CIFAR-100

and Food-101 datasets

and the network's regions of interest were visualized using Grad-CAM. On the ImageNet-1K

CIFAR-100

and Food-101 datasets

the SPAM improved the accuracy of the baseline network by up to about 1.08%

2.46%

and 1.09%

respectively. The results show that the performance of the network embedded with the SPAM components is greatly improved; compared to other commonly used lightweight attention mechanisms

the SPAM always works better; the SPAM can really induce the networks to pay more attention to the target object regions and accurately improve the expression ability of the networks.

关键词

Keywords

references

GU Jiuxiang, WANG Zhenhua, KUEN J, et al. Recent advances in convolutional neural networks [J]. Pattern Recognition, 2018, 77: 354-377.

LECUN Y, BOTTOU L, BENGIO Y, et al. Gradient-based learning applied to document recognition [J]. Proceedings of the IEEE, 1998, 86(11): 2278-2324.

KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks [J]. Communications of the ACM, 2017, 60(6): 84-90.

LECUN Y, BENGIO Y, HINTON G. Deep learning [J]. Nature, 2015, 521(7553): 436-444.

张宸嘉, 朱磊, 俞璐. 卷积神经网络中的注意力机制综述 [J]. 计算机工程与应用, 2021, 57(20): 64-72.

ZHANG Chenjia, ZHU Lei, YU Lu. Review of attention mechanism in convolutional neural networks [J]. Computer Engineering and Applications, 2021, 57(20): 64-72.

GUO Menghao, XU Tianxing, LIU Jiangjiang, et al. Attention mechanisms in computer vision: a survey [J]. Computational Visual Media, 2022, 8(3): 331-368.

WANG Fei, JIANG Mengqing, QIAN Chen, et al. Residual attention network for image classification [C]//2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ, USA: IEEE, 2017: 6450-6458.

ZHU Minghao, JIAO Licheng, LIU Fang, et al. Residual spectral-spatial attention network for hyperspectral image classification [J]. IEEE Transactions on Geoscience and Remote Sensing, 2021, 59(1): 449-462.

HUANG Zilong, WANG Xinggang, HUANG Lichao, et al. CCNet: criss-cross attention for semantic segmentation [C]//2019 IEEE/CVF International Conference on Computer Vision. Piscataway, NJ, USA: IEEE, 2019: 603-612.

刘文祥, 舒远仲, 唐小敏, 等. 采用双注意力机制Deeplabv3+算法的遥感影像语义分割 [J]. 热带地理, 2020, 40(2): 303-313.

LIU Wenxiang, SHU Yuanzhong, TANG Xiaomin, et al. Remote sensing image segmentation using dual attention mechanism Deeplabv3+ algorithm [J]. Tropical Geography, 2020, 40(2): 303-313.

LE V T, KIM Y G. Attention-based residual autoencoder for video anomaly detection [J]. Applied Intelligence, 2023, 53(3): 3240-3254.

PU Chunyu, HUANG Hong, YANG Liping. An attention-driven convolutional neural network-based multi-level spectral-spatial feature learning for hyperspectral image classification [J]. Expert Systems with Applications, 2021, 185: 115663.

HU Jie, SHEN Li, SUN Gang. Squeeze-and-excitation networks [C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway, NJ, USA: IEEE, 2018: 7132-7141.

张珂, 冯晓晗, 郭玉荣, 等. 图像分类的深度卷积神经网络模型综述 [J]. 中国图象图形学报, 2021, 26(10): 2305-2325.

ZHANG Ke, FENG Xiaohan, GUO Yurong, et al. Overview of deep convolutional neural networks for image classification [J]. Journal of Image and Graphics, 2021, 26(10): 2305-2325.

WANG Xiaolong, GIRSHICK R, GUPTA A, et al. Non-local neural networks [C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway, NJ, USA: IEEE, 2018: 7794-7803.

WOO S, PARK J, LEE J Y, et al. CBAM: convolu-tional block attention module [C]//Computer Vision-ECCV 2018. Berlin, Germany: Springer International Publishing, 2018: 3-19.

CHEN Long, ZHANG Hanwang, XIAO Jun, et al. SCA-CNN: spatial and channel-wise attention in convolutional networks for image captioning [C]//2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ, USA: IEEE, 2017: 6298-6306.

WANG Qilong, WU Banggu, ZHU Pengfei, et al. ECA-Net: efficient channel attention for deep convolutional neural networks [C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway, NJ, USA: IEEE, 2020: 11531-11539.

HOU Qibin, ZHOU Daquan, FENG Jiashi. Coordinate attention for efficient mobile network design [C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway, NJ, USA: IEEE, 2021: 13708-13717.

HE Kaiming, ZHANG Xiangyu, REN Shaoqing, et al. Spatial pyramid pooling in deep convolutional networks for visual recognition [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(9): 1904-1916.

HUANG Zhanchao, WANG Jianlin, FU Xuesong, et al. DC-SPP-YOLO: dense connection and spatial pyramid pooling based YOLO for object detection [J]. Information Sciences, 2020, 522: 241-258.

RUSSAKOVSKY O, DENG Jia, SU Hao, et al. ImageNet large scale visual recognition challenge [J]. International Journal of Computer Vision, 2015, 115(3): 211-252.

SELVARAJU R R, COGSWELL M, DAS A, et al. Grad-CAM: visual explanations from deep networks via gradient-based localization [C]//2017 IEEE International Conference on Computer Vision. Piscataway, NJ, USA: IEEE, 2017: 618-626.

PASZKE A, GROSS S, MASSA F, et al. PyTorch: an imperative style, high-performance deep learning library [C]//Advances in Neural Information Processing Systems. San Francisco, CA, USA: Curran Associates, Inc., 2019: 8024-8035.

HE Kaiming, ZHANG Xiangyu, REN Shaoqing, et al. Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ, USA: IEEE, 2016: 770-778.

RADOSAVOVIC I, KOSARAJU R P, GIRSHICK R, et al. Designing network design spaces[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway, NJ, USA: IEEE, 2020: 10425-10433.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

一种双阻尼小波赋能的可解释卷积神经网络在轴承故障诊断中的应用

采用双树复小波变换的可解释机械故障诊断方法

一种鲁棒的概率主成分分析方法

总体平均经验模式分解与1.5维谱方法的研究

冲击故障特征提取的非线性流形学习方法