Journal of Frontiers of Computer Science and Technology ›› 2023, Vol. 17 ›› Issue (3): 511-532.DOI: 10.3778/j.issn.1673-9418.2210035

• Frontiers·Surveys • Previous Articles     Next Articles

Survey of Few-Shot Image Classification Research

AN Shengbiao, GUO Yuqi, BAI Yu, WANG Tengbo   

  1. School of Information Science and Engineering, Hebei University of Science and Technology, Shijiazhuang 050018, China
  • Online:2023-03-01 Published:2023-03-01

小样本图像分类研究综述

安胜彪,郭昱岐,白 宇,王腾博   

  1. 河北科技大学 信息科学与工程学院,石家庄 050018

Abstract: In recent years, artificial intelligence algorithms represented by deep learning have achieved success in many fields by relying on large-scale datasets and huge computing resources. Among them, the image classification technology in the field of computer vision develops vigorously, and many mature visual task classification models emerge. All these models need to use a large number of annotated samples for training. However, in actual scena-rios, due to many restrictions, the amount of data is scarce, and it is often difficult to obtain high-quality annotated samples of corresponding scale. Therefore, how to use a small number of samples for learning has gradually become a research hotspot. In view of the classification task system, this paper reviews the current work related to few-shot image classification. Few-shot learning mainly adopts deep learning methods such as meta-learning, metric learning and data enhancement. This paper summarizes the research progress and typical technical models of few-shot image classification from supervised, semi-supervised and unsupervised levels, as well as the performance of these model methods on several public datasets, and makes comparative analysis from the mechanism, advantages, limitations, etc. Finally, the technical difficulties and future trends of few-shot image classification are discussed.

Key words: deep learning, supervised learning, meta-learning, metric learning, image classification

摘要: 近年来,借助大规模数据集和庞大的计算资源,以深度学习为代表的人工智能算法在诸多领域取得成功。其中计算机视觉领域的图像分类技术蓬勃发展,并涌现出许多成熟的视觉任务分类模型。这些模型均需要利用大量的标注样本进行训练,但在实际场景中因诸多限制导致数据量稀少,往往很难获得相应规模的高质量标注样本。因此如何使用少量样本进行学习已经逐渐成为当前的研究热点。针对分类任务系统梳理了当前小样本图像分类的相关工作,小样本学习主要采用元学习、度量学习和数据增强等深度学习方法。从有监督、半监督和无监督等层次归纳总结了小样本图像分类的研究进展和典型技术模型,以及这些模型方法在若干公共数据集上的表现,并从机制、优势、局限性等方面进行了对比分析。最后,讨论了当前小样本图像分类面临的技术难点以及未来的发展趋势。

关键词: 深度学习, 监督学习, 元学习, 度量学习, 图像分类