UNSUPERVISED DOMAIN ADAPTATION THROUGH SYNTHESIS FOR PERSON RE-IDENTIFICATION

被引:24
作者
Xiang, Suncheng [1 ]
Fu, Yuzhuo [1 ]
You, Guanjie [1 ]
Liu, Ting [1 ]
机构
[1] Shanghai Jiao Tong Univ, Sch Elect Informat & Elect Engn, Shanghai, Peoples R China
来源
2020 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO (ICME) | 2020年
基金
中国国家自然科学基金;
关键词
Re-identification; synthetic dataset; domain adaptation;
D O I
10.1109/icme46284.2020.9102822
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
Person re-identification is a hot topic because of its widespread applications in video surveillance and public security. However, it remains a challenging task because of drastic variations in illumination or background across surveillance cameras, which causes the current methods can not work well in real-world scenarios. In addition, due to the scarce dataset, many methods suffer from over-fitting to a different extent. To remedy the above two problems, firstly, we develop a data collector and labeler, which can generate the synthetic random scenes and simultaneously annotate them without any manpower. Based on it, we build a large-scale, diverse synthetic dataset. Secondly, we propose a novel unsupervised Re-ID method via domain adaptation, which can exploit the synthetic data to boost the performance of reidentification in a completely unsupervised way, and free humans from heavy data annotations. Extensive experiments show that our proposed method achieves the state-of-the-art performance on two benchmark datasets, and is very competitive with current cross-domain Re-ID method.
引用
收藏
页数:6
相关论文
共 50 条
[41]   Unsupervised Person Re-identification Using Unified Domanial Learning [J].
Zhang, Suian ;
Hu, Haifeng .
NEURAL PROCESSING LETTERS, 2023, 55 (06) :6887-6905
[42]   Unsupervised Person Re-identification via Diversity and Salience Clustering [J].
Long, Xiaoyi ;
Hu, Ruimin ;
Xu, Xin .
2021 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS (SMC), 2021, :2761-2766
[43]   Attribute discrimination combined with selected sample dropout for unsupervised domain adaptive person re-identification [J].
Liu, Chang ;
Li, Haoqi ;
He, Xuan ;
Yang, Guanzhong ;
Li, Zhiyong .
IMAGE AND VISION COMPUTING, 2024, 146
[44]   Selective transfer cycle GAN for unsupervised person re-identification [J].
Dai, Chengqiu ;
Peng, Cheng ;
Chen, Min .
MULTIMEDIA TOOLS AND APPLICATIONS, 2020, 79 (17-18) :12597-12613
[45]   Deep Domain Adaptation on Vehicle Re-identification [J].
Wang, Yifeng ;
Zeng, Dan .
2019 IEEE FIFTH INTERNATIONAL CONFERENCE ON MULTIMEDIA BIG DATA (BIGMM 2019), 2019, :416-420
[46]   Selective transfer cycle GAN for unsupervised person re-identification [J].
Chengqiu Dai ;
Cheng Peng ;
Min Chen .
Multimedia Tools and Applications, 2020, 79 :12597-12613
[47]   Neighbor similarity and soft-label adaptation for unsupervised cross-dataset person re-identification [J].
Zhao, Yiru ;
Lu, Hongtao .
NEUROCOMPUTING, 2020, 388 :246-254
[48]   An Unsupervised Domain Adaption Approach for Cross-Modality RGB-Infrared Person Re-Identification [J].
Chen, Qingshan ;
Quan, Zhenzhen ;
Li, Yujun ;
Zhai, Chao ;
Mozerov, Mikhail G. .
IEEE SENSORS JOURNAL, 2023, 23 (24) :31399-31413
[49]   Dual-level contrastive learning for unsupervised person re-identification [J].
Zhao, Yu ;
Shu, Qiaoyuan ;
Shi, Xi .
IMAGE AND VISION COMPUTING, 2023, 129
[50]   Camera-aware Embedding Refinement for unsupervised person re-identification [J].
Liu, Yimin ;
Qi, Meibin ;
Zhang, Yongle ;
Xu, Wenbo ;
Wu, Qiang .
KNOWLEDGE-BASED SYSTEMS, 2025, 314