基于Transformer目标检测研究综述

A Summary of Research on Target Detection Based on Transformer

目标检测是计算机视觉领域三大任务之一,同时也是计算机视觉领域内一个最基本和具有挑战性的热点课题,近一年来基于Transformer的目标检测算法研究引发热潮。简述Transformer框架在目标检测领域的研究状况,介绍了其基本原理、常用数据集和常用评价方法,并用多种公共数据集对不同算法进行对比以分析其优缺点,在综述研究基础上,结合行业应用对基于Transformer的目标检测进行总结与展望。

Target detection is one of the three major tasks in the field of computer vision.At the same time,it is also a basic and challenging hot topic in the field of computer vision.In almost a year,the research of object detection algorithms based on Transformer has caused a boom.This paper sketches the research status of Transformer framework in the field of target detection,introduces it’s basic principle,common data sets and common evaluation methods,and compares different algorithms with several public data sets,so as to analyze their advantages and disadvantages.On the basis of summarizing the research,also combined the industry application,this paper summarizes and prospects of the object detection based on Transformer.