Unsupervised Domain Adaptation with Background Shift Mitigating for Person Re-Identification
文献类型：期刊论文
| 作者 | Huang, Yan1 ; Wu, Qiang1; Xu, Jingsong1; Zhong, Yi2; Zhang, Zhaoxiang3
|
| 刊名 | INTERNATIONAL JOURNAL OF COMPUTER VISION
 |
| 出版日期 | 2021-05-12 |
| 页码 | 20 |
| 关键词 | Person re-identification Unsupervised domain adaptation Background suppression Image generation Virtual label estimation |
| ISSN号 | 0920-5691 |
| DOI | 10.1007/s11263-021-01474-8 |
| 通讯作者 | Wu, Qiang(qiang.wu@uts.edu.au) |
| 英文摘要 | Unsupervised domain adaptation has been a popular approach for cross-domain person re-identification (re-ID). There are two solutions based on this approach. One solution is to build a model for data transformation across two different domains. Thus, the data in source domain can be transferred to target domain where re-ID model can be trained by rich source domain data. The other solution is to use target domain data plus corresponding virtual labels to train a re-ID model. Constrains in both solutions are very clear. The first solution heavily relies on the quality of data transformation model. Moreover, the final re-ID model is trained by source domain data but lacks knowledge of the target domain. The second solution in fact mixes target domain data with virtual labels and source domain data with true annotation information. But such a simple mixture does not well consider the raw information gap between data of two domains. This gap can be largely contributed by the background differences between domains. In this paper, a Suppression of Background Shift Generative Adversarial Network (SBSGAN) is proposed to mitigate the gaps of data between two domains. In order to tackle the constraints in the first solution mentioned above, this paper proposes a Densely Associated 2-Stream (DA-2S) network with an update strategy to best learn discriminative ID features from generated data that consider both human body information and also certain useful ID-related cues in the environment. The built re-ID model is further updated using target domain data with corresponding virtual labels. Extensive evaluations on three large benchmark datasets show the effectiveness of the proposed method. |
| 资助项目 | Australian Government Research Training Program Scholarship ; Beijing Institute of Technology Research Fund Program for Young Scholars |
| WOS研究方向 | Computer Science |
| 语种 | 英语 |
| WOS记录号 | WOS:000650112400002 |
| 出版者 | SPRINGER |
| 资助机构 | Australian Government Research Training Program Scholarship ; Beijing Institute of Technology Research Fund Program for Young Scholars |
| 源URL | [http://ir.ia.ac.cn/handle/173211/45203]  |
| 专题 | 自动化研究所_智能感知与计算研究中心 |
| 通讯作者 | Wu, Qiang |
| 作者单位 | 1.Univ Technol Sydney, Sch Elect & Data Engn, Ultimo, Australia 2.Beijing Inst Technol, Sch Informat & Elect, Haidian, Peoples R China 3.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing, Peoples R China |
| 推荐引用方式 GB/T 7714 | Huang, Yan,Wu, Qiang,Xu, Jingsong,et al. Unsupervised Domain Adaptation with Background Shift Mitigating for Person Re-Identification[J]. INTERNATIONAL JOURNAL OF COMPUTER VISION,2021:20. |
| APA | Huang, Yan,Wu, Qiang,Xu, Jingsong,Zhong, Yi,&Zhang, Zhaoxiang.(2021).Unsupervised Domain Adaptation with Background Shift Mitigating for Person Re-Identification.INTERNATIONAL JOURNAL OF COMPUTER VISION,20. |
| MLA | Huang, Yan,et al."Unsupervised Domain Adaptation with Background Shift Mitigating for Person Re-Identification".INTERNATIONAL JOURNAL OF COMPUTER VISION (2021):20. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。