Multi-Granularity Mutual Learning Network for Object Re-Identification

doi:10.1109/TITS.2021.3137954

CORC > 自动化研究所 > 中国科学院自动化研究所 > 模式识别国家重点实验室 > 图像与视频分析团队

	Multi-Granularity Mutual Learning Network for Object Re-Identification
	Tu, Mingfei 2,3; Zhu, Kuan 2,3; Guo, Haiyun 1,2; Miao, Qinghai 3; Zhao, Chaoyang 1; Zhu, Guibo 2; Qiao, Honglin 4; Huang, Gaopan 4; Tang, Ming ; Wang, Jinqiao 1,2,3
刊名	IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
	2022-03-29
页码	12
关键词	Feature extraction Visualization Task analysis Intelligent transportation systems Image reconstruction Semantics Licenses Object re-identification mutual learning feature reconstruction solving jigsaw puzzle
ISSN号	1524-9050
DOI	10.1109/TITS.2021.3137954
通讯作者	Guo, Haiyun(haiyun.guo@nlpr.ia.ac.cn) ; Miao, Qinghai(miaoqh@ucas.ac.cn)
英文摘要	Object re-identification (re-ID), which is key and fundamental technology for intelligent transportation systems, is a challenging task including person re-ID and vehicle re-ID. It aims to retrieve a given target object from the gallery images captured by different cameras. In this task, it is necessary to extract fine-grained and discriminative features to deal with complex inter-class and intra-class variations caused by the changes of camera viewpoints and object poses. Existing methods focus on learning discriminative local features to improve the re-ID performance. Some state-of-the-art methods use key point detection model to locate local features, which also increases the additional computational cost as side effect. Another type of method focuses on how to learn features of different granularity from rigid stripes of different scales. However, there is little attention paid to how to effectively coalesce multi-granularity features without additional calculation cost. To tackle this issue, this paper proposes the Multi-granularity Mutual Learning Network (MMNet) and makes two contributions. 1) We introduce the multi-granularity jigsaw puzzle module into object re-ID to impel the network to learn local discriminative features from multiple visual granularities by breaking spatial correlation in original images. 2) We propose a parameter-free multi-scale feature reconstruction module to facilitate mutual learning of features at multiple grain levels, thereby both global features and local features have strong representation capabilities. Extensive experiments demonstrate the effectiveness of our proposed modules and the superiority of our method over various state-of-the-art methods on both person and vehicle re-ID benchmarks.
资助项目	Key-Area Research and Development Program of Guangdong Province[2019B010153001] ; National Natural Science Foundation of China[61772527] ; National Natural Science Foundation of China[61976210] ; National Natural Science Foundation of China[62002356] ; National Natural Science Foundation of China[62002357] ; National Natural Science Foundation of China[62076235] ; National Natural Science Foundation of China[62006230] ; Open Research Projects of Zhejiang Laboratory[2021KH0AB07] ; Alibaba Group through Alibaba Innovative Research Program
WOS关键词	VEHICLE REIDENTIFICATION
WOS研究方向	Engineering ; Transportation
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000777339700001
资助机构	Key-Area Research and Development Program of Guangdong Province ; National Natural Science Foundation of China ; Open Research Projects of Zhejiang Laboratory ; Alibaba Group through Alibaba Innovative Research Program
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/48198]
专题	自动化研究所_模式识别国家重点实验室_图像与视频分析团队
通讯作者	Guo, Haiyun; Miao, Qinghai
作者单位	1.Object Eye Inc, Beijing 100078, Peoples R China 2.Chinese Acad Sci, Natl Lab Pattern Recognit, Inst Automat, Beijing 100864, Peoples R China 3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100190, Peoples R China 4.Alibaba Cloud, Beijing 100102, Peoples R China
推荐引用方式 GB/T 7714	Tu, Mingfei,Zhu, Kuan,Guo, Haiyun,et al. Multi-Granularity Mutual Learning Network for Object Re-Identification[J]. IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS,2022:12.
APA	Tu, Mingfei.,Zhu, Kuan.,Guo, Haiyun.,Miao, Qinghai.,Zhao, Chaoyang.,...&Wang, Jinqiao.(2022).Multi-Granularity Mutual Learning Network for Object Re-Identification.IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS,12.
MLA	Tu, Mingfei,et al."Multi-Granularity Mutual Learning Network for Object Re-Identification".IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS (2022):12.