Improve Person Re-Identification With Part Awareness Learning
文献类型：期刊论文
| 作者 | Huang, Houjing6,7 ; Yang, Wenjie6,7; Lin, Jinbin2; Huang, Guan1,2; Xu, Jiamiao2,3,5; Wang, Guoli2; Chen, Xiaotang6,7; Huang, Kaiqi4,6,7
|
| 刊名 | IEEE TRANSACTIONS ON IMAGE PROCESSING
 |
| 出版日期 | 2020 |
| 卷号 | 29页码:7468-7481 |
| 关键词 | Person re-identification part awareness part segmentation multi-task learning |
| ISSN号 | 1057-7149 |
| DOI | 10.1109/TIP.2020.3003442 |
| 通讯作者 | Huang, Houjing(houjing.huang@nlpr.ia.ac.cn) |
| 英文摘要 | Person re-identification (ReID) aims to predict whether two images from different cameras belong to the same person. Due to low image quality and variance in view point and body pose, it remains a difficult task. To solve the task, a model is supposed to appropriately capture features that describe body regions for identification. With the simple intuition that explicitly incorporating ReID model with part awareness could be beneficial for learning a more discriminative feature space, we propose part segmentation as an assistant body perception task during the training of a ReID model. Specifically, we add a lightweight segmentation head to the backbone of ReID model during training, which is supervised with part labels. Note that our segmentation head is only introduced during training and that it does not change network input or the way of extracting ReID feature. Experiments show that part segmentation considerably improves the performance of ReID. Through quantitative and qualitative analyses, we further reveal that body part perception helps ReID model to capture a set of more diverse features from the body, with decreased similarity between part features and increased focus on different body regions. We experiment with various representative ReID models and achieve consistent improvement on several large-scale datasets including Market1501, CUHK03, DukeMTMC-reID and MSMT17. E.g. on MSMT17, our method increases Rank-1 Accuracy of GlobalPool-ResNet-50, PCB and MGN by 2.3%, 2.9% and 3.9%, respectively. Incorporated with MGN, our model achieves state-of-the-art performance, with Rank-1 Accuracy 95.8%, 78.8%, 90.0% and 84.0% on four datasets, respectively. |
| WOS关键词 | NETWORK |
| 资助项目 | National Key Research and Development Program of China[2016YFB1001005] ; National Natural Science Foundation of China[61673375] ; National Natural Science Foundation of China[61721004] ; National Natural Science Foundation of China[61876181] ; Projects of Chinese Academy of Science[QYZDB-SSW-JSC006] ; Youth Innovation Promotion Association CAS |
| WOS研究方向 | Computer Science ; Engineering |
| 语种 | 英语 |
| WOS记录号 | WOS:000553851400017 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| 资助机构 | National Key Research and Development Program of China ; National Natural Science Foundation of China ; Projects of Chinese Academy of Science ; Youth Innovation Promotion Association CAS |
| 源URL | [http://ir.ia.ac.cn/handle/173211/40262]  |
| 专题 | 智能系统与工程 |
| 通讯作者 | Huang, Houjing |
| 作者单位 | 1.Xforward AI Technol Co Ltd, Algorithm Dept, Beijing 100081, Peoples R China 2.Horizon Robot Inc, Beijing 100036, Peoples R China 3.DeepRouteai, Deep Learning Dept, Shenzhen 518000, Peoples R China 4.Chinese Acad Sci, Ctr Excellence Brain Sci & Intelligence Technol, Shanghai 200031, Peoples R China 5.Huazhong Univ Sci & Technol, Sch Elect Informat & Commun, Wuhan 430074, Peoples R China 6.Chinese Acad Sci, Inst Automat, Ctr Res Intelligent Syst & Engn, Beijing 100190, Peoples R China 7.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China |
| 推荐引用方式 GB/T 7714 | Huang, Houjing,Yang, Wenjie,Lin, Jinbin,et al. Improve Person Re-Identification With Part Awareness Learning[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2020,29:7468-7481. |
| APA | Huang, Houjing.,Yang, Wenjie.,Lin, Jinbin.,Huang, Guan.,Xu, Jiamiao.,...&Huang, Kaiqi.(2020).Improve Person Re-Identification With Part Awareness Learning.IEEE TRANSACTIONS ON IMAGE PROCESSING,29,7468-7481. |
| MLA | Huang, Houjing,et al."Improve Person Re-Identification With Part Awareness Learning".IEEE TRANSACTIONS ON IMAGE PROCESSING 29(2020):7468-7481. |
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。