计算机工程与应用 ›› 2021, Vol. 57 ›› Issue (16): 40-49.DOI: 10.3778/j.issn.1002-8331.2103-0306

• 热点与综述 • 上一篇    下一篇

基于弱监督学习的目标检测研究进展

杨辉,权冀川,梁新宇,王中伟   

  1. 1.陆军工程大学 指挥控制工程学院,南京 210007
    2.中国人民解放军73658部队
  • 出版日期:2021-08-15 发布日期:2021-08-16

Research Progress of Object Detection Based on Weakly Supervised Learning

YANG Hui, QUAN Jichuan, LIANG Xinyu, WANG Zhongwei   

  1. 1.Command & Control Engineering College, Army Engineering University of PLA, Nanjing 210007, China
    2.Unit 73658 of PLA, China
  • Online:2021-08-15 Published:2021-08-16

摘要:

随着卷积神经网络(Convolutional Neural Network,CNN)的不断发展,目标检测作为计算机视觉中最基本的技术,已取得了令人瞩目的进展。介绍了强监督目标检测算法对数据集标注精度要求高的现状。对基于弱监督学习的目标检测算法进行研究,按照不同的特征处理方法将该算法归为四类,并分析比较了各类算法的优缺点。通过实验比较了各类基于弱监督学习的目标检测算法的检测精度,并将其与主流的强监督目标检测算法进行了比较。展望了基于弱监督学习的目标检测算法未来的研究热点。

关键词: 弱监督学习, 目标检测, 多示例学习, 类激活图, 注意力机制, 伪标签

Abstract:

With the continuous development of Convolutional Neural Network(CNN), as the most basic technology in computer vision, object detection has made remarkable progress. Firstly, the current situation that the strong supervised object detection algorithm requires high precision for labeling datasets is introduced. Secondly, the object detection algorithm based on weakly supervised learning is studied. The algorithm is classified into four categories according to different feature processing methods, and the advantages and disadvantages of each algorithm are analyzed and compared. Thirdly, the detection accuracy of all kinds of object detection algorithms based on weakly supervised learning is compared through experiments. At the same time, it is compared with the mainstream strong supervised object detection algorithms. Finally, the future research hotspots of object detection algorithms based on weakly supervised learning are prospected.

Key words: weakly supervised learning, object detection, multi-instance learning, class activation map, attention mechanism, pseudo label