计算机科学与探索 ›› 2021, Vol. 15 ›› Issue (6): 1038-1048.DOI: 10.3778/j.issn.1673-9418.2011020

• 综述·探索 • 上一篇    下一篇

半监督深度学习图像分类方法研究综述

吕昊远,俞璐,周星宇,邓祥   

  1. 陆军工程大学 通信工程学院,南京 210007
  • 出版日期:2021-06-01 发布日期:2021-06-03

Review of Semi-supervised Deep Learning Image Classification Methods

LYU Haoyuan, YU Lu, ZHOU Xingyu, DENG Xiang   

  1. College of Communication Engineering, Army Engineering University of PLA, Nanjing 210007, China
  • Online:2021-06-01 Published:2021-06-03

摘要:

作为人工智能领域近十年来最受关注的技术之一,深度学习在诸多应用中取得了优异的效果,但目前的学习策略严重依赖大量的有标记数据。在许多实际问题中,获得众多有标记的训练数据并不可行,因此加大了模型的训练难度,但容易获得大量无标记的数据。半监督学习充分利用无标记数据,提供了在有限标记数据条件下提高模型性能的解决思路和有效方法,在图像分类任务中达到了很高的识别精准度。首先对于半监督学习进行概述,然后介绍了分类算法中常用的基本思想,重点对近年来基于半监督深度学习框架的图像分类方法,包括多视图训练、一致性正则、多样混合和半监督生成对抗网络进行全面的综述,总结多种方法共有的技术,分析比较不同方法的实验效果差异,最后思考当前存在的问题并展望未来可行的研究方向。

关键词: 半监督深度学习, 多视图训练, 一致性正则, 多样混合, 半监督生成对抗网络

Abstract:

As one of the most concerned technologies in the field of artificial intelligence in recent ten years, deep learning has achieved excellent results in many applications, but the current learning strategies rely heavily on a large number of labeled data. In many practical problems, it is not feasible to obtain a large number of labeled training data, so it increases the training difficulty of the model. But it is easy to obtain a large number of unlabeled data. Semi-supervised learning makes full use of unlabeled data, provides solutions and effective methods to improve the performance of the model under the condition of limited labeled data, and achieves high recognition accuracy in the task of image classification. This paper first gives an overview of semi-supervised learning, and then introduces the basic ideas commonly used in classification algorithms. It focuses on the comprehensive review of image classification methods based on semi-supervised deep learning framework in recent years, including multi- view training, consistency regularization, diversity mixing and semi-supervised generative adversarial networks. It summarizes the common technologies of various methods, analyzes and compares the differences of experimental results of different methods. Finally, this paper thinks about the existing problems and looks forward to the feasible research direction in the future.

Key words: semi-supervised deep learning, multi-view training, consistency regularization, diversity mixing, semi-supervised generative adversarial networks