Institutional Repository of Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Two-Level Attention Network With Multi-Grain Ranking Loss for Vehicle Re-Identification | |
Guo, Haiyun1,2![]() ![]() ![]() | |
Source Publication | IEEE TRANSACTIONS ON IMAGE PROCESSING
![]() |
ISSN | 1057-7149 |
2019-09 | |
Volume | 28Issue:9Pages:4328-4338 |
Abstract | Vehicle re-identification (re-ID) aims to identify the same vehicle across multiple non-overlapping cameras, which is rather a challenging task. On the one hand, subtle changes in viewpoint and illumination condition can make the same vehicle look much different. On the other hand, different vehicles, even different vehicle models, may look quite similar. In this paper, we propose a novel Two-level Attention network supervised by a Multi-grain Ranking loss (TAMR) to learn an efficient feature embedding for the vehicle re-ID task. The two-level attention network consisting of hard part-level attention and soft pixel-level attention can adaptively extract discriminative features from the visual appearance of vehicles. The former one is designed to localize the salient vehicle parts, such as windscreen and car head. The latter one gives an additional attention refinement at pixel level to focus on the distinctive characteristics within each part. In addition, we present a multi-grain ranking loss to further enhance the discriminative ability of learned features. We creatively take the multi-grain relationship between vehicles into consideration. Thus, not only the discrimination between different vehicles but also the distinction between different vehicle models is constrained. Finally, the proposed network can learn a feature space, where both intra-class compactness and interclass discrimination are well guaranteed. Extensive experiments demonstrate the effectiveness of our approach and we achieve state-of-the-art results on two challenging datasets, including VehicleID and Vehicle-1M. |
Keyword | Two-level attention network multi-grain ranking loss vehicle re-identification feature embedding |
DOI | 10.1109/TIP.2019.2910408 |
Indexed By | SCI |
Language | 英语 |
Funding Project | National Natural Science Foundation of China[61806200] ; National Natural Science Foundation of China[61772527] ; National Natural Science Foundation of China[61772527] ; National Natural Science Foundation of China[61806200] |
WOS Research Area | Computer Science ; Engineering |
WOS Subject | Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic |
WOS ID | WOS:000473641100011 |
Publisher | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
Citation statistics | |
Document Type | 期刊论文 |
Identifier | http://ir.ia.ac.cn/handle/173211/26856 |
Collection | 模式识别国家重点实验室_图像与视频分析 |
Corresponding Author | Zhu, Kuan |
Affiliation | 1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100864, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100190, Peoples R China |
First Author Affilication | Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China |
Corresponding Author Affilication | Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China |
Recommended Citation GB/T 7714 | Guo, Haiyun,Zhu, Kuan,Tang, Ming,et al. Two-Level Attention Network With Multi-Grain Ranking Loss for Vehicle Re-Identification[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2019,28(9):4328-4338. |
APA | Guo, Haiyun,Zhu, Kuan,Tang, Ming,&Wang, Jinqiao.(2019).Two-Level Attention Network With Multi-Grain Ranking Loss for Vehicle Re-Identification.IEEE TRANSACTIONS ON IMAGE PROCESSING,28(9),4328-4338. |
MLA | Guo, Haiyun,et al."Two-Level Attention Network With Multi-Grain Ranking Loss for Vehicle Re-Identification".IEEE TRANSACTIONS ON IMAGE PROCESSING 28.9(2019):4328-4338. |
Files in This Item: | Download All | |||||
File Name/Size | DocType | Version | Access | License | ||
two-level attention (2562KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | View Download |
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment