CASIA OpenIR  > 紫东太初大模型研究中心  > 图像与视频分析
Multi-Granularity Mutual Learning Network for Object Re-Identification
Tu, Mingfei1,2; Zhu, Kuan1,2; Guo, Haiyun2,3; Miao, Qinghai1; Zhao, Chaoyang3; Zhu, Guibo2; Qiao, Honglin4; Huang, Gaopan4; Tang, Ming; Wang, Jinqiao1,2,3
Source PublicationIEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
ISSN1524-9050
2022-03-29
Pages12
Abstract

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.

KeywordFeature extraction Visualization Task analysis Intelligent transportation systems Image reconstruction Semantics Licenses Object re-identification mutual learning feature reconstruction solving jigsaw puzzle
DOI10.1109/TITS.2021.3137954
WOS KeywordVEHICLE REIDENTIFICATION
Indexed BySCI
Language英语
Funding ProjectKey-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
Funding OrganizationKey-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
WOS Research AreaEngineering ; Transportation
WOS SubjectEngineering, Civil ; Engineering, Electrical & Electronic ; Transportation Science & Technology
WOS IDWOS:000777339700001
PublisherIEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Sub direction classification图像视频处理与分析
planning direction of the national heavy laboratory视觉信息处理
Paper associated data
Citation statistics
Cited Times:13[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/48199
Collection紫东太初大模型研究中心_图像与视频分析
紫东太初大模型研究中心
Corresponding AuthorGuo, Haiyun; Miao, Qinghai
Affiliation1.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100190, Peoples R China
2.Chinese Acad Sci, Natl Lab Pattern Recognit, Inst Automat, Beijing 100864, Peoples R China
3.Object Eye Inc, Beijing 100078, Peoples R China
4.Alibaba Cloud, Beijing 100102, Peoples R China
First Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Corresponding Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Recommended Citation
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.
Files in This Item: Download All
File Name/Size DocType Version Access License
Multi-Granularity_Mu(4360KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Tu, Mingfei]'s Articles
[Zhu, Kuan]'s Articles
[Guo, Haiyun]'s Articles
Baidu academic
Similar articles in Baidu academic
[Tu, Mingfei]'s Articles
[Zhu, Kuan]'s Articles
[Guo, Haiyun]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Tu, Mingfei]'s Articles
[Zhu, Kuan]'s Articles
[Guo, Haiyun]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Multi-Granularity_Mutual_Learning_Network_for_Object_Re-Identification.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.