电子学报

• •    

基于多分支瓶颈结构的轻量型图像分类算法研究

苏田田, 王慧敏, 张小凤   

  1. 陕西师范大学物理学与信息技术学院,陕西 西安 710119
  • 收稿日期:2022-08-05 修回日期:2022-11-10 出版日期:2022-11-25
    • 作者简介:
    • 苏田田 男,1996年出生于甘肃省.2019年在西北师范大学获得学士学位.现为陕西师范大学研究生,主要研究方向为计算机视觉和深度学习. E-mail: sutcarl@hotmail.com
      王慧敏 女,1997年出生于陕西省.2019年在陕西师范大学获得学士学位.现为陕西师范大学研究生,主要研究方向为图像分类. E-mail: 1164994333@qq.com
      张小凤 (通讯作者) 女,1971年出生于陕西省.现为陕西师范大学物理学与信息技术学院教授,博士生导师.主要研究方向为超声工程、智能信号处理与检测.
    • 基金资助:
    • 国家自然科学基金 (11874252)

Research on Lightweight Image Classification Algorithm Based on Multi-branch Bottleneck Structure

SU Tian-tian, WANG Hui-min, ZHANG Xiao-feng   

  1. School of Physics and Information Technology,Shaanxi Normal University,Xi'an,Shaanxi 710119,China
  • Received:2022-08-05 Revised:2022-11-10 Online:2022-11-25
    • Supported by:
    • National Natural Science Foundation of China (11874252)

摘要:

传统卷积神经网络存在着参数量大、训练耗时长、轻量级模型的识别准确度不足的问题.本文提出了一种基于ResNet网络的多分支结构轻量化网络(Residual multi-branch structured Network,RemulbNet),通过在残差结构的主干中使用多分支结构增加特征多样性,利用变体的深度可分离卷积缩减模型参数量,采用Mish激活函数增加网络的非线性表达能力,在有效减少模型体积的情况下,提升网络的分类准确率.利用图像识别数据库,对网络性能进行测试.研究表明,对于5分类花卉识别问题,RemulbNet相比ResNet网络识别准确率提高3.9%,模型参数量减小71%,模型体积减小77%,缩短了约40%训练耗时;与轻量级网络(MobileNet v2和ShuffleNet v2)相比,RemulbNet在识别准确度、模型体积、训练时长和不同的图像分类数据集上都表现出优良的性能.

关键词: 轻量化网络, 多分支瓶颈结构, Mish激活函数, 深度可分离卷积, 图像分类, 卷积神经网络

Abstract:

The traditional convolutional neural networks have many problems, such as large number of parameters, long training time, and insufficient recognition accuracy of the lightweight models. Based on ResNet network, a lightweight network named RemulbNet(Residual multi-branch structured Network) with multi-branch structure, which increases feature diversity with multi-branch structure in the backbone of the residual structure, reduces the number of model parameters with the depth-separable convolution of variants, and also increases the nonlinear expression capability of the network with Mish activation function. These measures can effectively reduce the model volume and improve the classification accuracy of the network. Using the image recognition database, the network performance is tested. For 5 categories of flower identification, RemulbNet improves the recognition accuracy by 3.9%, reduces the number of model parameters by 71%, reduces the model volume by 77%, and shortens the training time by about 40% compared with the ResNet network. Facing different image classification datasets, RemulbNet also shows excellent performance in terms of recognition accuracy, model volume, training time compared with the lightweight networks(MobileNet v2 and ShuffleNet v2).

Key words: lightweight networks, multi-branch bottleneck structure, mish activation function, deep separable convolution, image classification, convolutional neural network

中图分类号: