Computer Engineering and Applications ›› 2023, Vol. 59 ›› Issue (10): 48-64.DOI: 10.3778/j.issn.1002-8331.2211-0133

• Research Hotspots and Reviews • Previous Articles     Next Articles

Survey of Transformer-Based Object Detection Algorithms

LI Jian, DU Jianqiang, ZHU Yanchen, GUO Yongkun   

  1. College of Computer Science, Jiangxi University of Chinese Medicine, Nanchang 330004, China
  • Online:2023-05-15 Published:2023-05-15

基于Transformer的目标检测算法综述

李建,杜建强,朱彦陈,郭永坤   

  1. 江西中医药大学 计算机学院,南昌 330004

Abstract: Transformer is a kind of deep learning framework with strong modeling and parallel computing capabilities. At present, object detection algorithm based on Transformer has become a hotspot. In order to further explore new ideas and directions, this paper summarizes the existing object detection algorithm based on Transformer as well as a variety of object detection data sets and their application scenarios. This paper describes the correlation algorithms for Transformer based object detection from four aspects, i.e. feature extraction, object estimation, label matching policy and application of algorithm, compares the Transformer algorithm with the object detection algorithm based on convolutional neural network, analyzes the advantages and disadvantages of Transformer in object detection task, and proposes a general framework for Transformer based object detection model. Finally, the prospect of development trend of Transformer in the field of object detection is put forward.

Key words: Transformer, image processing, object detection, deep learning, convolutional neural network(CNN)

摘要: 深度学习框架Transformer具有强大的建模能力和并行计算能力,目前基于Transformer的目标检测算法已经成为研究的热点。为了进一步探索目标检测的新思路、新方向,对基于Transformer的目标检测算法进行了归纳总结。概述了多种目标检测数据集及其应用场景,从特征学习、目标估计、标签匹配策略和算法应用四方面梳理了Transformer目标检测的相关算法,并与基于卷积神经网络的目标检测算法进行对比,分析了Transformer在目标检测任务中的优点和局限性,并提出了Transformer目标检测模型的一般性框架。对Transformer在目标检测领域中的发展趋势进行了展望。

关键词: Transformer, 图像处理, 目标检测, 深度学习, 卷积神经网络(CNN)