Deep Conditional Distribution Learning for Age Estimation

doi:10.1109/TIFS.2021.3114066

	Deep Conditional Distribution Learning for Age Estimation
	Sun, Haomiao 1,2; Pan, Hongyu 3; Han, Hu 1; Shan, Shiguang 1,2,4
刊名	IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY
	2021
卷号	16 页码:4679-4690
关键词	Estimation Task analysis Faces Face recognition Learning systems Adaptation models Information processing Conditional modeling distribution learning label ambiguity age estimation attribute estimation
ISSN号	1556-6013
DOI	10.1109/TIFS.2021.3114066
英文摘要	Age estimation is a challenging task not only because face appearance is affected by illumination, pose, and expression, but also because there exists age label ambiguity among different demographic groups. In this work, we first revisit different label distribution learning (LDL) based age estimation methods and propose a more general formulation, which can unify individual LDL-based age estimation methods, as well as the traditional regression, classification, and ranking based age estimation methods. Based on such a general formulation, we propose a novel deep conditional distribution learning (DCDL) method, which can flexibly leverage a varying number of auxiliary face attributes to achieve adaptive age-related feature learning and improve age estimation robustness against the challenges above. Experimental results on multiple age estimation datasets (MORPH II, AgeDB, FG-NET, MegaAge-Asian, CLAP2016, UTK-Face, and LFW+) show that the proposed approach outperforms the state-of-the-art age estimation methods by a large margin. In addition, the proposed approach can generalize well to other human attributes estimation tasks, like height, weight, and body mass index (BMI) estimation.
资助项目	National Key Research and Development Program of China[2017YFA0700800] ; National Natural Science Foundation of China[61732004] ; National Natural Science Foundation of China[62176249] ; Youth Innovation Promotion Association CAS[2018135]
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:000704109600002
内容类型	期刊论文
源URL	[http://119.78.100.204/handle/2XEOYT63/16965]
专题	中国科学院计算技术研究所
通讯作者	Han, Hu
作者单位	1.Chinese Acad Sci, Key Lab Intelligent Informat Proc, Inst Comp Technol, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 3.DAMO Acad, Autonomous Driving Lab, Alibaba Grp, Beijing 100102, Peoples R China 4.Peng Cheng Natl Lab, Shenzhen 518055, Peoples R China
推荐引用方式 GB/T 7714	Sun, Haomiao,Pan, Hongyu,Han, Hu,et al. Deep Conditional Distribution Learning for Age Estimation[J]. IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY,2021,16:4679-4690.
APA	Sun, Haomiao,Pan, Hongyu,Han, Hu,&Shan, Shiguang.(2021).Deep Conditional Distribution Learning for Age Estimation.IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY,16,4679-4690.
MLA	Sun, Haomiao,et al."Deep Conditional Distribution Learning for Age Estimation".IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY 16(2021):4679-4690.