基于特征重用残差块的图像分类模型
DOI:
作者:
作者单位:

兰州交通大学 电子与信息工程学院

作者简介:

通讯作者:

中图分类号:

TP391.41

基金项目:

国家自然科学基金项目(61662043)


An Image Classification Model Based on Feature Reuse Residual Blocks
Author:
Affiliation:

1.School of Electronic and Information Engineering, Lanzhou Jiaotong University;2.School of Electronic and Information Engineering,Lanzhou Jiaotong University;3.China

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    在当今图像数据大规模普及的背景下,准确且快速地进行图像分类仍是一项具有挑战性的任务。本研究提出了一种名为IDCNet的新型基于特征重用残差块的分类模型。该模型采用卷积神经网络作为主干结构,并在分支部分引入特征重用残余块(feature reuse residual block,FRB)和深度扩张卷积(depthwise dilated convolution,DDC)单元,以扩展信息流,丰富特征的多样性,从而有效提升模型的分类性能。实验结果表明,在CIFAR-10、CIFAR-100和Fashion MNIST数据集上,该模型优于其它对比方法,在图像分类领域具有应用和借鉴的价值。

    Abstract:

    In the context of the widespread availability of image data today, accurate and fast image classification remains a challenging task. A novel classification model called IDCNet is proposed in this research. The model is based on the reuse of residual blocks for feature extraction. A convolutional neural network is utilized as the backbone structure of the model. In the branching part, feature reuse residual blocks (FRB) and depth dilated convolutions (DDC) units are incorporated to enhance the flow of information and enrich the diversity of features. As a result, the classification performance of the model is effectively improved. Experimental results demonstrate that the proposed model outperforms other comparative methods on CIFAR-10, CIFAR-100, and Fashion MNIST datasets. This showcases the potential and value of the model in the field of image classification.

    参考文献
    相似文献
    引证文献
引用本文

张忠林,赵磊. 基于特征重用残差块的图像分类模型[J]. 科学技术与工程, , ():

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2024-01-11
  • 最后修改日期:2024-01-24
  • 录用日期:2024-01-26
  • 在线发布日期:
  • 出版日期:
×
亟待确认版面费归属稿件,敬请作者关注