Heterogeneous Face Attribute Estimation: A Deep Multi-Task Learning Approach

doi:10.1109/TPAMI.20172738004

	Heterogeneous Face Attribute Estimation: A Deep Multi-Task Learning Approach
	Han, Hu 1,2; Jain, Anil K.3; Wang, Fang 1; Shan, Shiguang 1,2,4; Chen, Xilin 1,2
	2018-11-01
发表期刊	IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
ISSN	0162-8828
卷号	40 期号:11 页码:2597-2609
摘要	Face attribute estimation has many potential applications in video surveillance, face retrieval, and social media. While a number of methods have been proposed for face attribute estimation, most of them did not explicitly consider the attribute correlation and heterogeneity (e.g., ordinal versus nominal and holistic versus local) during feature representation learning. In this paper, we present a Deep Multi-Task Learning (DMTL) approach to jointly estimate multiple heterogeneous attributes from a single face image. In DMTL, we tackle attribute correlation and heterogeneity with convolutional neural networks (CNNs) consisting of shared feature learning for all the attributes, and category-specific feature learning for heterogeneous attributes. We also introduce an unconstrained face database (LFW+), an extension of public-domain LFW, with heterogeneous demographic attributes (age, gender, and race) obtained via crowdsourcing. Experimental results on benchmarks with multiple face attributes (MORPH II, LFW+, CelebA, LFWA, and FotW) show that the proposed approach has superior performance compared to state of the art. Finally, evaluations on a public-domain face database (LAP) with a single attribute show that the proposed approach has excellent generalization ability.
关键词	Face recognition heterogeneous attribute estimation attribute correlation attribute heterogeneity multi-task learning
DOI	10.1109/TPAMI.20172738004
收录类别	SCI
语种	英语
资助项目	National Basic Research Program of China (973 Program)[2015CB351802] ; Natural Science Foundation of China[61390511] ; Natural Science Foundation of China[61732004] ; Natural Science Foundation of China[61672496] ; Natural Science Foundation of China[61650202] ; CAS-INRIA JRPs[GJHZ1843]
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000446683700006
出版者	IEEE COMPUTER SOC
引用统计	被引频次：142[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/4809
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Shan, Shiguang
作者单位	1.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 3.Michigan State Univ, Dept Comp Sci & Engn, E Lansing, MI 48824 USA 4.CAS Ctr Excellence Brain Sci & Intelligence Tech, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Han, Hu,Jain, Anil K.,Wang, Fang,et al. Heterogeneous Face Attribute Estimation: A Deep Multi-Task Learning Approach[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2018,40(11):2597-2609.
APA	Han, Hu,Jain, Anil K.,Wang, Fang,Shan, Shiguang,&Chen, Xilin.(2018).Heterogeneous Face Attribute Estimation: A Deep Multi-Task Learning Approach.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,40(11),2597-2609.
MLA	Han, Hu,et al."Heterogeneous Face Attribute Estimation: A Deep Multi-Task Learning Approach".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 40.11(2018):2597-2609.