Journal of Frontiers of Computer Science and Technology ›› 2023, Vol. 17 ›› Issue (1): 53-73.DOI: 10.3778/j.issn.1673-9418.2206020

• Frontiers·Surveys • Previous Articles     Next Articles

Survey of Few-Shot Object Detection

LIU Chunlei, CHEN Tian‘en2,3, WANG Cong, JIANG Shuwen, CHEN Dong   

  1. 1. School of Computer, Electronics and Information, Guangxi University, Nanning?530004, China
    2. Research Center of Information Technology, Beijing Academy of Agriculture and Forestry Sciences, Beijing 100097, China
    3. National Engineering Research Center for Information Technology in Agriculture, Beijing 100097, China
  • Online:2023-01-01 Published:2023-01-01



  1. 1. 广西大学 计算机与电子信息学院,南宁 530004
    2. 北京市农林科学院 信息技术研究中心,北京 100097
    3. 国家农业信息化工程技术研究中心,北京 100097

Abstract: Object detection as a hot field in computer vision, usually requires a large number of labeled images for model training, which will cost a lot of manpower and material resources. At the same time, due to the inherent long-tailed distribution of data in the real world, the number of samples of most objects is relatively small, such as many uncommon diseases, etc., and it is difficult to obtain a large number of labeled images. In this regard, few-shot object detection only needs to provide a small amount of annotation information to detect objects of interest. This paper makes a detailed review of few-shot object detection methods. Firstly, the development of general target detection and its existing problems are reviewed, the concept of few-shot object detection is introduced, and other tasks related to few-shot object detection are differentiated and explained. Then, two classical paradigms based on transfer learning and meta-learning for existing few-shot object detection are introduced. According to the improvement strategies of different methods, few-shot object detection is divided into four types: attention mechanism, graph convolutional neural network, metric learning and data augmentation. The public datasets and evaluation metrics used in these methods are explained. Advantages, disadvantages, applicable scenarios of different methods, and performance on different datasets are compared and analyzed. Finally, the practical application fields and future research trends of few-shot object detection are discussed.

Key words: object detection, few-shot object detection, meta-learning, transfer learning

摘要: 目标检测是计算机视觉方向的热点领域,其通常需要大量的标注图像用于模型训练,这将花费大量的人力和物力来实现。同时,由于真实世界中的数据存在固有的长尾分布,大部分对象的样本数量都比较稀少,比如众多非常见疾病等,很难获得大量的标注图像。小样本目标检测只需要提供少量的标注信息,就能够检测出感兴趣的对象,对小样本目标检测方法做了详细综述。首先回顾了通用目标检测的发展及其存在的问题,从而引出小样本目标检测的概念,对同小样本目标检测相关的其他任务做了区分阐述。之后介绍了现有小样本目标检测基于迁移学习和基于元学习的两种经典范式。根据不同方法的改进策略,将小样本目标检测分为基于注意力机制、图卷积神经网络、度量学习和数据增强四种类型,对这些方法中使用到的公开数据集和评估指标进行了说明,对比分析了不同方法的优缺点、适用场景以及在不同数据集上的性能表现。最后讨论了小样本目标检测的实际应用领域和未来的研究趋势。

关键词: 目标检测, 小样本目标检测, 元学习, 迁移学习