Deep Rank-Consistent Pyramid Model for Enhanced Crowd Counting

doi:10.1109/TNNLS.2023.3336774

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

	Deep Rank-Consistent Pyramid Model for Enhanced Crowd Counting
	Gao, Jiaqi 1; Huang, Zhizhong 1; Lei, Yiming 1; Shan, Hongming 2,3,4; Wang, James Z.5; Wang, Fei-Yue 6,7,8; Zhang, Junping 1
刊名	IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
	2023-12-13
页码	14
关键词	Crowd counting feature pyramid ranking semi-supervised learning
ISSN号	2162-237X
DOI	10.1109/TNNLS.2023.3336774
通讯作者	Wang, Fei-Yue(feiyue.wang@ia.ac.cn) ; Zhang, Junping(jpzhang@fudan.edu.cn)
英文摘要	Most conventional crowd counting methods utilize a fully-supervised learning framework to establish a mapping between scene images and crowd density maps. They usually rely on a large quantity of costly and time-intensive pixel-level annotations for training supervision. One way to mitigate the intensive labeling effort and improve counting accuracy is to leverage large amounts of unlabeled images. This is attributed to the inherent self-structural information and rank consistency within a single image, offering additional qualitative relation supervision during training. Contrary to earlier methods that utilized the rank relations at the original image level, we explore such rank-consistency relation within the latent feature spaces. This approach enables the incorporation of numerous pyramid partial orders, strengthening the model representation capability. A notable advantage is that it can also increase the utilization ratio of unlabeled samples. Specifically, we propose a Deep Rank-consistEnt pyrAmid Model (), which makes full use of rank consistency across coarse-to-fine pyramid features in latent spaces for enhanced crowd counting with massive unlabeled images. In addition, we have collected a new unlabeled crowd counting dataset, FUDAN-UCC, comprising 4000 images for training purposes. Extensive experiments on four benchmark datasets, namely UCF-QNRF, ShanghaiTech PartA and PartB, and UCF-CC-50, show the effectiveness of our method compared with previous semi-supervised methods.
资助项目	National Natural Science Foundation of China
WOS关键词	PEDESTRIAN DETECTION ; NETWORK
WOS研究方向	Computer Science ; Engineering
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:001127680600001
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/173211/55009]
专题	多模态人工智能系统全国重点实验室
通讯作者	Wang, Fei-Yue; Zhang, Junping
作者单位	1.Fudan Univ, Sch Comp Sci, Shanghai Key Lab Intelligent Informat Proc, Shanghai 200433, Peoples R China 2.Fudan Univ, Inst Sci & Technol Brain Inspired Intelligence, Shanghai 200433, Peoples R China 3.Fudan Univ, MOE Frontiers Ctr Brain Sci, Shanghai 200433, Peoples R China 4.Shanghai Ctr Brain Sci & Brain Inspired Technol, Shanghai 201210, Peoples R China 5.Penn State Univ, Coll Informat Sci & Technol, University Pk, PA 16802 USA 6.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China 7.Macau Univ Sci & Technol, Inst Syst Engn, Macau, Peoples R China 8.Qingdao Acad Intelligent Ind, Qingdao 266109, Peoples R China
推荐引用方式 GB/T 7714	Gao, Jiaqi,Huang, Zhizhong,Lei, Yiming,et al. Deep Rank-Consistent Pyramid Model for Enhanced Crowd Counting[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2023:14.
APA	Gao, Jiaqi.,Huang, Zhizhong.,Lei, Yiming.,Shan, Hongming.,Wang, James Z..,...&Zhang, Junping.(2023).Deep Rank-Consistent Pyramid Model for Enhanced Crowd Counting.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,14.
MLA	Gao, Jiaqi,et al."Deep Rank-Consistent Pyramid Model for Enhanced Crowd Counting".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2023):14.