Unsupervised Horizontal Pyramid Similarity Learning for Cross-Domain Adaptive Person Re-Identification
Unsupervised Horizontal Pyramid Similarity Learning for Cross-Domain Adaptive Person Re-Identification
复制标题
用于跨域自适应行人重新识别的无监督水平金字塔相似性学习
DOI：
10.1109/access.2021.3093083
复制
发表时间：
2021
期刊：
影响因子：
3.9
通讯作者：
Ning Gai
中科院分区：
文献类型：
--
作者：
Wenhui Dong;Peishu Qu;Chunsheng Liu;Yanke Tang;Ning Gai
Although person re-identification has made great progress, unsupervised cross-domain adaptive person re-identification is still a challenging problem. With no labeled data in target domain, the performance may have a significant drop. In this paper, we propose an unsupervised cross-domain adaptive person re-identification framework based on horizontal pyramid similarity learning (UHPS). Firstly, horizontal pyramid features are extracted by dividing the deep feature maps into different number of partial feature bins. These feature bins with diverse scales can incorporate not only the global information but also local information in different spatial scales, making the framework more robust in complex environment. Then, horizontal pyramid similarity learning is proposed with the mechanism of fusing together the internal similarity of the target domain and the similarity between the source domain and target domain. Finally, the unsupervised clustering algorithm DBSCAN embeded with the horizontal pyramid similarity is employed to select training data in the target domain and estimate the pseudo labels in each training iteration, for the purpose of adapting the framework to the target domain. The results on Market1501 and DukeMTMC-reID confirm that the proposed framework can adapt to the target domain effectively and outperforms the state-of-the-art unsupervised cross domain person re-identification approaches.
登录
查看更多内容
影响因子：
10.6
作者：
Hantao Yao;Shiliang Zhang;Richang Hong;Yongdong Zhang;Changsheng Xu;Q. Tian
通讯作者：
Hantao Yao;Shiliang Zhang;Richang Hong;Yongdong Zhang;Changsheng Xu;Q. Tian
DOI：
10.1109/cvpr.2019.00375
发表时间：
2019-06
期刊：
2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
影响因子：
--
作者：
Q. Yang;Hong-Xing Yu;Ancong Wu;Weishi Zheng
通讯作者：
Q. Yang;Hong-Xing Yu;Ancong Wu;Weishi Zheng
DOI：
--
发表时间：
2017-03
期刊：
ArXiv
影响因子：
--
作者：
Alexander Hermans;Lucas Beyer;B. Leibe
通讯作者：
Alexander Hermans;Lucas Beyer;B. Leibe
DOI：
10.1007/978-3-030-58621-8_27
发表时间：
2019-12
期刊：
--
影响因子：
--
作者：
Shengcai Liao;Ling Shao
通讯作者：
Shengcai Liao;Ling Shao
DOI：
10.1007/978-3-030-58571-6_35
发表时间：
2020-07
期刊：
ArXiv
影响因子：
--
作者：
Yunpeng Zhai;Qixiang Ye;Shijian Lu;Mengxi Jia;Rongrong Ji;Yonghong Tian
通讯作者：
Yunpeng Zhai;Qixiang Ye;Shijian Lu;Mengxi Jia;Rongrong Ji;Yonghong Tian