Journal article · 2021 · Open access

图像分类的深度卷积神经网络模型综述

Ke Zhang, Xiaohan Feng, Guo Yurong, Yukun Su, Zhao Kai, Zhenbing Zhao, Zhanyu Ma, Qiaolin Ding

Journal of Image and Graphics, 26(10), 2305–2325 · Published 1 January 2021 · DOI 10.11834/jig.200302

Free PDFView at the publisherCite this paper

In brief

“图像分类的深度卷积神经网络模型综述” is a 2021 journal article by Ke Zhang and 7 co-authors, published in Journal of Image and Graphics. OpenAlex counts 48 citations as of 16 November 2026, which puts it in the top 2% of works published in 2021 by citations. It is open access: the full text is free to read at Journal of Image and Graphics.

Citations
48
Most cited in
2024 (16)
Field-weighted impact
2.84
Authors
8

Abstract

图像分类是计算机视觉中的一项重要任务,传统的图像分类方法具有一定的局限性。随着人工智能技术的发展,深度学习技术越来越成熟,利用深度卷积神经网络对图像进行分类成为研究热点,图像分类的深度卷积神经网络结构越来越多样,其性能远远好于传统的图像分类方法。本文立足于图像分类的深度卷积神经网络模型结构,根据模型发展和模型优化的历程,将深度卷积神经网络分为经典深度卷积神经网络模型、注意力机制深度卷积神经网络模型、轻量级深度卷积神经网络模型和神经网络架构搜索模型等4类,并对各类深度卷积神经网络模型结构的构造方法和特点进行了全面综述,对各类分类模型的性能进行了对比与分析。虽然深度卷积神经网络模型的结构设计越来越精妙,模型优化的方法越来越强大,图像分类准确率在不断刷新的同时,模型的参数量也在逐渐降低,训练和推理速度不断加快。然而深度卷积神经网络模型仍有一定的局限性,本文给出了存在的问题和未来可能的研究方向,即深度卷积神经网络模型主要以有监督学习方式进行图像分类,受到数据集质量和规模的限制,无监督式学习和半监督学习方式的深度卷积神经网络模型将是未来的重点研究方向之一;深度卷积神经网络模型的速度和资源消耗仍不尽人意,应用于移动式设备具有一定的挑战性;模型的优化方法以及衡量模型优劣的度量方法有待深入研究;人工设计深度卷积神经网络结构耗时耗力,神经架构搜索方法将是未来深度卷积神经网络模型设计的发展方向。

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Zhang, K., Feng, X., Yurong, G., Su, Y., Kai, Z., Zhao, Z., Ma, Z., & Ding, Q. (2021). 图像分类的深度卷积神经网络模型综述. Journal of Image and Graphics, 26(10), 2305–2325. https://doi.org/10.11834/jig.200302

MLA 9

Zhang, Ke, et al. “图像分类的深度卷积神经网络模型综述.” Journal of Image and Graphics, vol. 26, no. 10, 2021, pp. 2305–2325. https://doi.org/10.11834/jig.200302.

Chicago

Zhang, Ke, Xiaohan Feng, Guo Yurong, Yukun Su, Zhao Kai, Zhenbing Zhao, Zhanyu Ma, and Qiaolin Ding. 2021. “图像分类的深度卷积神经网络模型综述.” Journal of Image and Graphics 26 (10): 2305–2325. https://doi.org/10.11834/jig.200302.

Harvard

Zhang, K. et al. (2021) ‘图像分类的深度卷积神经网络模型综述’, Journal of Image and Graphics, 26(10), pp. 2305–2325. doi:10.11834/jig.200302.

IEEE

K. Zhang et al., “图像分类的深度卷积神经网络模型综述,” Journal of Image and Graphics, vol. 26, no. 10, pp. 2305–2325, 2021, doi: 10.11834/jig.200302.

BibTeX

@article{zhang2021,
  title     = {{图像分类的深度卷积神经网络模型综述}},
  author    = {Zhang, Ke and Feng, Xiaohan and Yurong, Guo and Su, Yukun and Kai, Zhao and Zhao, Zhenbing and Ma, Zhanyu and Ding, Qiaolin},
  journal   = {Journal of Image and Graphics},
  year      = {2021},
  volume    = {26},
  number    = {10},
  pages     = {2305--2325},
  doi       = {10.11834/jig.200302},
  url       = {https://doi.org/10.11834/jig.200302}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Citations by year

YearCitationsShare of the best year
202266
20231515
20241616
202566
202655

Its field-weighted citation impact is 2.84: it has been cited 2.84 times as often as the average work of the same field, type and year (1.00 is the world average).

Topic and keywords

Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications

  • image classification
  • deep convolutional neural networks
  • attention mechanism
  • lightweight neural networks
  • neural architecture search
  • model optimization
  • supervised learning
  • unsupervised learning

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Zhang, K., Feng, X., Yurong, G., Su, Y., Kai, Z., Zhao, Z., Ma, Z., & Ding, Q. (2021). 图像分类的深度卷积神经网络模型综述. Journal of Image and Graphics, 26(10), 2305–2325. https://doi.org/10.11834/jig.200302

How many times has this paper been cited?

48 times, according to OpenAlex on 16 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access: read the free full text at Journal of Image and Graphics.

Who wrote this paper?

Ke Zhang, Xiaohan Feng, Guo Yurong, Yukun Su, Zhao Kai, Zhenbing Zhao, Zhanyu Ma, Qiaolin Ding.

What is the DOI of this paper?

10.11834/jig.200302. The permanent link is https://doi.org/10.11834/jig.200302.

Bibliographic data from OpenAlex (CC0), last checked 16 November 2026. ResearchGuru does not host this paper; the links go to the publisher or the repository that does.