模式识别与人工智能
2025年4月4日 星期五   首 页     期刊简介     编委会     投稿指南     伦理声明     联系我们                                                                English
模式识别与人工智能  2022, Vol. 35 Issue (10): 904-914    DOI: 10.16451/j.cnki.issn1003-6059.202210004
深度学习在图像与视觉的应用 最新目录| 下期目录| 过刊浏览| 高级检索 |
基于语义伪标签和双重特征存储库的无监督跨模态行人重识别
孙锐1,2, 余益衡1,2, 张磊1,2, 张旭东1
1.合肥工业大学 计算机与信息学院 合肥230601;
2.合肥工业大学 工业安全与应急技术安徽省重点实验室 合肥 230009
Unsupervised Cross-Modality Person Re-identification Based on Semantic Pseudo-Label and Dual Feature Memory Banks
SUN Rui1,2, YU Yiheng1,2, ZHANG Lei1,2, ZHANG Xudong1,2
1. School of Computer Science and Information Engineering, Hefei University of Technology, Hefei 230601;
2. Anhui Key Laboratory of Industry Safety and Emergency Technology, Hefei University of Technology, Hefei 230009

全文: PDF (767 KB)   HTML (1 KB) 
输出: BibTeX | EndNote (RIS)      
摘要 现有的有监督可见光-近红外行人重识别方法需要大量人力资源去除手工标注数据,容易受到标注数据场景的限制,难以满足真实多变应用场景的泛化性.因此,文中提出基于语义伪标签和双重特征存储库的无监督跨模态行人重识别方法.首先,提出基于对比学习框架的预训练方法,利用可见光行人图像和其生成的辅助灰度图像进行训练.利用该预训练方法获取对颜色变化具有鲁棒性的语义特征提取网络.然后,使用DBSCAN(Density-Based Spatial Clustering of Applications with Noise)聚类方法生成语义伪标签.相比现有的伪标签生成方法,文中提出的语义伪标签在生成过程中充分利用跨模态数据之间的结构信息,减少跨模态数据颜色变化带来的模态差异.此外,文中还构建实例级困难样本特征存储库和中心级聚类特征存储库,充分利用困难样本特征和聚类特征,让模型对噪声伪标签具有更强的鲁棒性.在SYSU-MM01、RegDB两个跨模态数据集上的实验验证文中方法的有效性.
服务
把本文推荐给朋友
加入我的书架
加入引用管理器
E-mail Alert
RSS
作者相关文章
孙锐
余益衡
张磊
张旭东
关键词 无监督跨模态行人重识别语义伪标签双重特征存储库深度学习    
Abstract:The existing supervised visible infrared person re-identification methods require a lot of human resources to manually label the data and they fail to adapt to the generalization of real and changeable application scenes due to the limitation by the labeled data scene. In this paper, an unsupervised cross-modality person re-identification method based on semantic pseudo-label and dual feature memory banks is proposed. Firstly, a pre-training method based on the contrast learning framework is proposed, using the visible image and its generated auxiliary gray image for training. The pre-training method is employed to obtain the semantic feature extraction network that is robust to color changes. Then,semantic pseudo-label is generated by density based spatial clustering of applications with noise (DBSCAN) clustering method. Compared with the existing pseudo-label generation methods, the proposed method makes full use of the structural information between the cross-modality data in the generation process, and thus the modality discrepancy caused by the color change of the cross-modality data is reduced. In addition, an instance-level hard sample feature memory bank and a centroid-level clustering feature memory bank are constructed to make the model more robust to noise pseudo-label by hard sample features and clustering features. Experimental results obtained on two cross-modality datasets, SYSU-MM01 and RegDB, demonstrate the effectiveness of the proposed method.
Key wordsUnsupervised Cross-Modality Person Re-identification    Semantic Pseudo-Label    Dual Feature Memory Bank    Deep Learning   
收稿日期: 2022-05-05     
ZTFLH: TP 391  
基金资助:国家自然科学基金面上项目(No.61876057)、安徽省自然科学基金项目(No.2208085MF158)、安徽省重点研发计划-科技强警专项项目(No.202004d07020012)
通讯作者: 孙 锐,博士,教授,主要研究方向为计算机视觉、机器学习.E-mail:sunrui @hfut.edu.cn.   
作者简介: 余益衡,硕士研究生,主要研究方向为图像信息处理、计算机视觉.E-mail:2020111040@mail.hfut.edu.cn. 张 磊,硕士研究生,主要研究方法为图像信息处理、计算机视觉.E-mail:2020171121@mail.hfut.edu.cn. 张旭东,博士,教授,主要研究方向为智能信息处理、机器视觉.E-mail:xudong@hfut.edu.cn.
引用本文:   
孙锐, 余益衡, 张磊, 张旭东. 基于语义伪标签和双重特征存储库的无监督跨模态行人重识别[J]. 模式识别与人工智能, 2022, 35(10): 904-914. SUN Rui, YU Yiheng, ZHANG Lei, ZHANG Xudong. Unsupervised Cross-Modality Person Re-identification Based on Semantic Pseudo-Label and Dual Feature Memory Banks. Pattern Recognition and Artificial Intelligence, 2022, 35(10): 904-914.
链接本文:  
http://manu46.magtech.com.cn/Jweb_prai/CN/10.16451/j.cnki.issn1003-6059.202210004      或     http://manu46.magtech.com.cn/Jweb_prai/CN/Y2022/V35/I10/904
版权所有 © 《模式识别与人工智能》编辑部
地址:安微省合肥市蜀山湖路350号 电话:0551-65591176 传真:0551-65591176 Email:bjb@iim.ac.cn
本系统由北京玛格泰克科技发展有限公司设计开发 技术支持:support@magtech.com.cn