计算机科学与探索 ›› 2021, Vol. 15 ›› Issue (10): 1830-1842.DOI: 10.3778/j.issn.1673-9418.2103019

• 综述·探索 • 上一篇    下一篇

细粒度图像分类的深度学习方法

李祥霞,吉晓慧,李彬   

  1. 1. 广东财经大学 信息学院,广州 510320
    2. 华南理工大学 自动化科学与工程学院,广州 510641
  • 出版日期:2021-10-01 发布日期:2021-09-30

Deep Learning Method for Fine-Grained Image Categorization

LI Xiangxia, JI Xiaohui, LI Bin   

  1. 1. School of Information, Guangdong University of Finance & Economics, Guangzhou 510320, China
    2. School of Automation Science and Engineering, South China University of Technology, Guangzhou 510641, China
  • Online:2021-10-01 Published:2021-09-30

摘要:

细粒度图像分类旨在从某一类别的图像中区分出其子类别,通常细粒度数据集具有类间相似和类内差异大的特点,这使得细粒度图像分类任务更加具有挑战性。随着深度学习的不断发展,基于深度学习的细粒度图像分类方法表现出更强大的特征表征能力和泛化能力,能够获得更准确、稳定的分类结果,因此受到了越来越多研究人员的关注和研究。首先,从细粒度图像分类的研究背景出发,介绍了细粒度图像分类的难点和研究意义。其次,从基于强监督和弱监督两个角度,综述了基于深度学习的细粒度图像分类算法的研究进展,并介绍了多种典型的分类性能优秀的算法。此外,进一步论述了目前关于YOLO、多尺度CNN和生成对抗网络(GAN)等前沿深度学习模型在细粒度图像识别方面的应用,并且对比了最新的相关细粒度图像的数据增强方法的分类效果以及在复杂场景下不同类型的细粒度识别方法的性能特点分析。最后,通过对算法的分类性能进行对比和总结,探讨了未来发展方向和面临的挑战。

关键词: 细粒度图像分类, 深度学习, 卷积神经网络(CNN), 特征提取

Abstract:

Fine-grained image categorization aims to distinguish the sub-categories from a certain category of images. Generally, fine-grained data sets have the characteristics of the intra-class similarity and inter-class variation, which makes the task of fine-grained image categorization more challenging. With the increasing development of deep learning, the methods of fine-grained image categorization based on deep learning exhibit more powerful feature representation and generalization capabilities, and can obtain more accurate and stable classification results. Therefore, deep learning has been attracting more and more attentions and research from the researchers in the fine-grained image categorization. In this paper, starting from the background of fine-grained image categorization,  the difficulties and the meaning of fine-grained image categorization are introduced. Then, from the perspectives of strong supervision and weak supervision, this paper reviews the research progress of fine-grained image classification algorithms based on deep learning, and a variety of typical classification algorithms with excellent performance are introduced. In addition, the YOLO (you only look once), multi-scale CNN (convolutional neural network), and GAN (generative adversarial networks) model are further discussed in the application of fine-grained image categorization, the perfor-mance of the latest relevant fine-grained data augmentation methods is compared and an analysis of different types of fine-grained categorization methods is made under complex scenarios. Finally, by comparing and summarizing the categorization algorithms, the future improvement directions and challenges are discussed.

Key words: fine-grained image categorization, deep learning, convolutional neural network (CNN), feature extraction