A Unified Framework for Biphasic Facial Age Translation With Noisy-Semantic Guided Generative Adversarial Networks

doi:10.1109/TIFS.2022.3164187

CORC > 自动化研究所 > 中国科学院自动化研究所 > 智能感知与计算研究中心

	A Unified Framework for Biphasic Facial Age Translation With Noisy-Semantic Guided Generative Adversarial Networks
	Sun, Muyi 1; Wang, Jian 1; Liu, Jian 2; Li, Jianshu 2; Chen, Tao 2; Sun, Zhenan 1
刊名	IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY
	2022
卷号	17 页码:1513-1527
关键词	Semantics Faces Face recognition Training Noise measurement Layout Image synthesis Biphasic facial age translation noisy semantic injection generative adversarial network attention mechanism feature disentanglement
ISSN号	1556-6013
DOI	10.1109/TIFS.2022.3164187
通讯作者	Sun, Zhenan(znsun@nlpr.ia.ac.cn)
英文摘要	Biphasic facial age translation aims at predicting the appearance of the input face at any age. Facial age translation has received considerable research attention in the last decade due to its practical value in cross-age face recognition and various entertainment applications. However, most existing methods model age changes between holistic images, regardless of the human face structure and the age-changing patterns of individual facial components. Consequently, the lack of semantic supervision will cause infidelity of generated faces in detail. To this end, we propose a unified framework for biphasic facial age translation with noisy-semantic guided generative adversarial networks. Structurally, we project the class-aware noisy semantic layouts to "soft" latent maps for the following injection operation on the individual facial parts. In particular, we introduce two sub-networks, ProjectionNet and ConstraintNet. ProjectionNet introduces the low-level structural semantic information with noise map and produces "soft" latent maps. ConstraintNet disentangles the high-level spatial features to constrain the "soft" latent maps, which endows more age-related context into the "soft" latent maps. Specifically, attention mechanism is employed in ConstraintNet for feature disentanglement. Meanwhile, in order to mine the strongest mapping ability of the network, we embed two types of learning strategies in the training procedure, supervised self-driven generation and unsupervised condition-driven cycle-consistent generation. As a result, extensive experiments conducted on MORPH and CACD datasets demonstrate the prominent ability of our proposed method which achieves state-of-the-art performance.
资助项目	National Natural Science Foundation of China[U1836217]
WOS关键词	PERCEPTION ; MANIPULATION
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:000782797200003
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/173211/48354]
专题	自动化研究所_智能感知与计算研究中心
通讯作者	Sun, Zhenan
作者单位	1.Chinese Acad Sci, Ctr Res Intelligent Percept & Comp, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 2.Ant Grp, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Sun, Muyi,Wang, Jian,Liu, Jian,et al. A Unified Framework for Biphasic Facial Age Translation With Noisy-Semantic Guided Generative Adversarial Networks[J]. IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY,2022,17:1513-1527.
APA	Sun, Muyi,Wang, Jian,Liu, Jian,Li, Jianshu,Chen, Tao,&Sun, Zhenan.(2022).A Unified Framework for Biphasic Facial Age Translation With Noisy-Semantic Guided Generative Adversarial Networks.IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY,17,1513-1527.
MLA	Sun, Muyi,et al."A Unified Framework for Biphasic Facial Age Translation With Noisy-Semantic Guided Generative Adversarial Networks".IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY 17(2022):1513-1527.