Global and Local Consistent Wavelet-Domain Age Synthesis

doi:10.1109/TIFS.2019.2907973

	Global and Local Consistent Wavelet-Domain Age Synthesis
	Li, Peipei 1,2; Hu, Yibo1 ; He, Ran1,2 ; Sun, Zhenan1,2
刊名	IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY
	2019-11-01
卷号	14 期号:11 页码:2943-2957
关键词	Age synthesis wavelet transform generative adversarial network global and local features
ISSN号	1556-6013
DOI	10.1109/TIFS.2019.2907973
通讯作者	He, Ran(rhe@nlpr.ia.ac.cn)
英文摘要	Age synthesis is a challenging task due to the complicated and non-linear transformation in the human aging process. Aging information is usually reflected in local facial parts, such as wrinkles at the eye corners. However, these local facial parts contribute less in previous GAN-based methods for age synthesis. To address this issue, we propose a wavelet-domain global and local consistent age generative adversarial network (WaveletGLCA-GAN), in which one global specific network and three local specific networks are integrated together to capture both global topology information and local texture details of human faces. Different from the mast existing methods that modeling age synthesis in image domain, we adopt wavelet transform to depict the textual information in frequency domain. Moreover, five types of losses are adopted: 1) adversarial loss aims to generate realistic wavelets; 2) identity preserving loss aims to better preserve identity information; 3) age preserving loss aims to enhance the accuracy of age synthesis; 4) pixel-wise loss aims to preserve the background information of the input face; and 5) the total variation regularization aims to remove ghosting artifacts. Our method is evaluated on three face aging datasets, including CACD2000, Morph, and FG-NET. Qualitative and quantitative experiments show the superiority of the proposed method over other state-of-the-arts.
资助项目	State Key Development Program[2016YFB1001001] ; State Key Development Program[2017YFC0821602] ; State Key Development Program[2016YFB1001000] ; National Natural Science Foundation of China[61622310] ; National Natural Science Foundation of China[61427811] ; National Natural Science Foundation of China[61573360] ; Beijing Natural Science Foundation[JQ18017]
WOS关键词	PERCEPTION
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:000474549100001
资助机构	State Key Development Program ; National Natural Science Foundation of China ; Beijing Natural Science Foundation
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/26882]
专题	中国科学院自动化研究所
通讯作者	He, Ran
作者单位	1.Inst Automat Chinese Acad Sci, Ctr Res Intelligent Percept & Comp, CAS Ctr Excellence Brain Sci & Intelligence Techn, Inst Automat,Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
推荐引用方式 GB/T 7714	Li, Peipei,Hu, Yibo,He, Ran,et al. Global and Local Consistent Wavelet-Domain Age Synthesis[J]. IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY,2019,14(11):2943-2957.
APA	Li, Peipei,Hu, Yibo,He, Ran,&Sun, Zhenan.(2019).Global and Local Consistent Wavelet-Domain Age Synthesis.IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY,14(11),2943-2957.
MLA	Li, Peipei,et al."Global and Local Consistent Wavelet-Domain Age Synthesis".IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY 14.11(2019):2943-2957.