题名 | Viewpoint-Aware Loss with Angular Regularization for Person Re-Identification |
作者 | |
通讯作者 | Zhihui,Zhu |
DOI | |
发表日期 | 2020-04-03
|
会议名称 | AAAI
|
ISSN | 2374-3468
|
EISSN | 2374-3468
|
会议录名称 | |
卷号 | 34
|
会议日期 | 2020
|
会议地点 | Virtual-only Conference
|
出版地 | 2275 E BAYSHORE RD, STE 160, PALO ALTO, CA 94303 USA
|
出版者 | |
摘要 | Although great progress in supervised person re-identification (Re-ID) has been made recently, due to the viewpoint variation of a person, Re-ID remains a massive visual challenge. Most existing viewpoint-based person Re-ID methods project images from each viewpoint into separated and unrelated sub-feature spaces. They only model the identity-level distribution inside an individual viewpoint but ignore the underlying relationship between different viewpoints. To address this problem, we propose a novel approach, called \textit{Viewpoint-Aware Loss with Angular Regularization }(\textbf{VA-reID}). Instead of one subspace for each viewpoint, our method projects the feature from different viewpoints into a unified hypersphere and effectively models the feature distribution on both the identity-level and the viewpoint-level. In addition, rather than modeling different viewpoints as hard labels used for conventional viewpoint classification, we introduce viewpoint-aware adaptive label smoothing regularization (VALSR) that assigns the adaptive soft label to feature representation. VALSR can effectively solve the ambiguity of the viewpoint cluster label assignment. Extensive experiments on the Market1501 and DukeMTMC-reID datasets demonstrated that our method outperforms the state-of-the-art supervised Re-ID methods. |
学校署名 | 其他
|
语种 | 其他
|
相关链接 | [来源记录] |
收录类别 | |
资助项目 | National Key Research and Development Program of China[2016YFB1001002]
; NSFC[61522115,"U1811461"]
; Guangdong Province Science and Technology Innovation Leading Talents[2016TX03X157]
; Guangzhou Research Project[201902010037]
|
WOS研究方向 | Computer Science
; Education & Educational Research
|
WOS类目 | Computer Science, Artificial Intelligence
; Computer Science, Interdisciplinary Applications
; Education, Scientific Disciplines
|
WOS记录号 | WOS:000668126805071
|
Scopus记录号 | 2-s2.0-85106591880
|
来源库 | 人工提交
|
引用统计 |
被引频次[WOS]:52
|
成果类型 | 会议论文 |
条目标识符 | http://sustech.caswiz.com/handle/2SGJ60CL/226092 |
专题 | 南方科技大学 工学院_计算机科学与工程系 |
作者单位 | 1.Sun Yat-sen University, Shenzhen, China 2.Tencent Youtu Lab, Shanghai, China 3.Southern University of Science and Technology, Shenzhen, China |
推荐引用方式 GB/T 7714 |
Zhihui,Zhu,Xinyang,Jiang,Feng,Zheng,et al. Viewpoint-Aware Loss with Angular Regularization for Person Re-Identification[C]. 2275 E BAYSHORE RD, STE 160, PALO ALTO, CA 94303 USA:Association for the Advancement of Artificial Intelligence (AAAI),2020.
|
条目包含的文件 | 条目无相关文件。 |
|
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。
修改评论