Visual Place Recognition via a Multitask Learning Method With Attentive Feature Aggregation

doi:10.1109/TCDS.2022.3206500

CORC > 自动化研究所 > 中国科学院自动化研究所 > 多模态人工智能系统全国重点实验室

	Visual Place Recognition via a Multitask Learning Method With Attentive Feature Aggregation
	Guan, Peiyu 2,3; Cao, Zhiqiang 2,3; Yu, Junzhi 1; Tan, Min 2,3; Wang, Shuo 2,3
刊名	IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL SYSTEMS
	2023-09-01
卷号	15 期号:3 页码:1263-1278
关键词	Attentive feature aggregation multitask learning visual place recognition
ISSN号	2379-8920
DOI	10.1109/TCDS.2022.3206500
通讯作者	Cao, Zhiqiang(zhiqiang.cao@ia.ac.cn)
英文摘要	Visual place recognition has gained popularity in recent years. Mainstream convolutional neural network-based methods formulate it as a ranking task and optimize it in the paradigm of deep metric learning, however, the ranking-motivated losses concern only the ranking relationship for each query image and the compactness of intraplace feature distribution is seldom considered. It is still challenging due to varying viewpoints, illuminations, and even dynamic objects. In this article, a novel multitask learning framework is proposed, which combines the existing triplet ranking task and our designed binary classification task to jointly optimize the network for better generalization capability. Specifically, a binary classification network with the corresponding binary cross-entropy loss is designed in the classification task. In this way, the intraplace feature compactness and interplace feature separability are reinforced. At the testing stage, this classification network is discarded without increasing the computation cost. Furthermore, an attention module is presented to promote the network to concentrate on the salient regions by assigning different importance to each spatial position. Our method achieves the top-10 recalls of 97.27%, 94.6%, and 96.93% on Pitts250k-test, Tokyo 24/7, and TokyoTM-val data sets, respectively. Extensive experiments prove that the proposed network can learn discriminative global features with better robustness to viewpoints and environmental variations.
资助项目	National Natural Science Foundation of China[62073322] ; National Natural Science Foundation of China[61633020]
WOS关键词	IMAGE ; NETVLAD ; NETWORK
WOS研究方向	Computer Science ; Robotics ; Neurosciences & Neurology
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:001089186500023
资助机构	National Natural Science Foundation of China
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/54391]
专题	多模态人工智能系统全国重点实验室
通讯作者	Cao, Zhiqiang
作者单位	1.Peking Univ, Coll Engn, Dept Adv Mfg & Robot, State Key Lab Turbulence & Complex Syst, Beijing 100871, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 3.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Guan, Peiyu,Cao, Zhiqiang,Yu, Junzhi,et al. Visual Place Recognition via a Multitask Learning Method With Attentive Feature Aggregation[J]. IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL SYSTEMS,2023,15(3):1263-1278.
APA	Guan, Peiyu,Cao, Zhiqiang,Yu, Junzhi,Tan, Min,&Wang, Shuo.(2023).Visual Place Recognition via a Multitask Learning Method With Attentive Feature Aggregation.IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL SYSTEMS,15(3),1263-1278.
MLA	Guan, Peiyu,et al."Visual Place Recognition via a Multitask Learning Method With Attentive Feature Aggregation".IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL SYSTEMS 15.3(2023):1263-1278.