Efficient Group-n Encoding and Decoding for Facial Age Estimation

doi:10.1109/TPAMI.2017.2779808

CORC > 自动化研究所 > 中国科学院自动化研究所 > 模式识别国家重点实验室 > 生物识别与安全技术研究中心

	Efficient Group-n Encoding and Decoding for Facial Age Estimation
	Zichang Tan 1,2; Jun Wan1 ; Zhen Lei1 ; Ruicong Zhi 3; Guodong Guo 4; Stan Z. Li1
刊名	IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
	2018-11-01
卷号	40 期号:11 页码:2610-2623
关键词	Age estimation deep learning convolutional neural network age grouping data imbalance
ISSN号	0162-8828
DOI	10.1109/TPAMI.2017.2779808
通讯作者	Wan, Jun(jun.wan@nlpr.ia.ac.cn)
英文摘要	Different ages are closely related especially among the adjacent ages because aging is a slow and extremely non-stationary process with much randomness. To explore the relationship between the real age and its adjacent ages, an age group-n encoding (AGEn) method is proposed in this paper. In our model, adjacent ages are grouped into the same group and each age corresponds to n groups. The ages grouped into the same group would be regarded as an independent class in the training stage. On this basis, the original age estimation problem can be transformed into a series of binary classification sub-problems. And a deep Convolutional Neural Networks (CNN) with multiple classifiers is designed to cope with such sub-problems. Later, a Local Age Decoding (LAD) strategy is further presented to accelerate the prediction process, which locally decodes the estimated age value from ordinal classifiers. Besides, to alleviate the imbalance data learning problem of each classifier, a penalty factor is inserted into the unified objective function to favor the minority class. To compare with state-of-the-art methods, we evaluate the proposed method on FG-NET. MORPH II, CACD and Chalearn LAP 2015 databases and it achieves the best performance.
资助项目	National Key Research and Development Plan[2016YFC0801002] ; Chinese National Natural Science Foundation Projects[61502491] ; Chinese National Natural Science Foundation Projects[61473291] ; Chinese National Natural Science Foundation Projects[61572501] ; Chinese National Natural Science Foundation Projects[61572536] ; Chinese National Natural Science Foundation Projects[61673052] ; Science and Technology Development Fund of Macau[112/2014/A3] ; Science and Technology Development Fund of Macau[151/2017/A] ; Science and Technology Development Fund of Macau[152/2017/A] ; NVIDIA GPU donation program ; AuthenMetric RD Funds
WOS关键词	LEAST-SQUARES REGRESSION ; RECOGNITION ; MANIFOLD ; MODELS
WOS研究方向	Computer Science ; Engineering
语种	英语
出版者	IEEE COMPUTER SOC
WOS记录号	WOS:000446683700007
资助机构	National Key Research and Development Plan ; Chinese National Natural Science Foundation Projects ; Science and Technology Development Fund of Macau ; NVIDIA GPU donation program ; AuthenMetric RD Funds
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/22024]
专题	自动化研究所_模式识别国家重点实验室_生物识别与安全技术研究中心
作者单位	1.Center for Biometrics and Security Research & National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences 2.University of Chinese Academy of Sciences 3.School of Computer and Communication Engineering, University of Science and Technology Beijing 4.Lane Department of Computer Science and Electrical Engineering, West Virginia University
推荐引用方式 GB/T 7714	Zichang Tan,Jun Wan,Zhen Lei,et al. Efficient Group-n Encoding and Decoding for Facial Age Estimation[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2018,40(11):2610-2623.
APA	Zichang Tan,Jun Wan,Zhen Lei,Ruicong Zhi,Guodong Guo,&Stan Z. Li.(2018).Efficient Group-n Encoding and Decoding for Facial Age Estimation.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,40(11),2610-2623.
MLA	Zichang Tan,et al."Efficient Group-n Encoding and Decoding for Facial Age Estimation".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 40.11(2018):2610-2623.