###
计算机系统应用:2020,29(1):256-260
本文二维码信息
码上扫一扫!
半监督单样本深度行人重识别方法
(河海大学 计算机与信息学院, 南京 211100)
Semi-Supervised Person Re-Identification with One-Sample
(College of Computer and Information, HOHAI University, Nanjing 211100, China)
摘要
图/表
参考文献
相似文献
本文已被:浏览 481次   下载 351
投稿时间:2019-06-20    修订日期:2019-07-16
中文摘要: 本文提出一种采用单样本训练的行人重识别方法,在迭代的过程中采用一种渐进学习框架,充分利用有标签数据和无标签数据的特性来优化模型.本文方法主要分为以下3个步骤:(1)训练卷积神经网络来不断优化模型;(2)样本评估:通过本文提出的抽样策略,使用多个模型共同训练,共同挑选出较优的伪标签数据;(3)进行下一轮的训练更新数据.在训练的过程中,我们训练数据由有标签数据、伪标签数据,映射标签数据三部分组成,使用三组数据进行联合学习,每组数据对应使用相应的损失函数对模型进行优化,并且随着迭代的进行,伪标签数据和映射标签数据总是不断更新.在使用单样本训练条件下,rank-1=65.3,mAP=45.6.当训练数据的标注率提升至40%时,rank-1=83.8,mAP=64.9.实验结果表明:本文提出的半监督行人重识别方法可以在使用更少标签数据的情况下,提供与完全监督学习方法相媲美的结果,充分体现了本方法的有效性.
Abstract:In this study, we propose a one-sample person re-identification method, which adopts a progressive learning framework in the process of iteration in order to making full use of the characteristics of labeled data and unlabeled data to optimize the model. In this framework, we iteratively train convolutional neural network to update the model and utilize multiple-model training together to select the reliable pseudo-label data during label estimation. Then, we update training data for the next round of training. The training data is splited into three parts: labeled data, pseudo-labeled data, and indexed-labeled data. We set up the corresponding loss function for each set of data and update the CNN model by the joint training on the three parts. In the progress of iteration, the pseudo-labeled data and index-labeled data are constantly updated. Under the one-sample set, rank-1=65.3, mAP=45.6. When the rate of labeled data is increased to 40%, rank-1=83.8, mAP=64.9. The result indicates that the semi-supervised person re-identification method proposed in this study can provide excellent results comparable to the supervised learning method with less labeled data, which fully demonstrates the effectiveness of the method.
文章编号:7270     中图分类号:    文献标志码:
基金项目:
引用文本:
单纯,王敏.半监督单样本深度行人重识别方法.计算机系统应用,2020,29(1):256-260
SHAN Chun,WANG Min.Semi-Supervised Person Re-Identification with One-Sample.COMPUTER SYSTEMS APPLICATIONS,2020,29(1):256-260

用微信扫一扫

用微信扫一扫