中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 智能感知与计算研究中心
A(3)GAN: An Attribute-Aware Attentive Generative Adversarial Network for Face Aging

文献类型：期刊论文

作者Liu, Yunfan1,3; Li, Qi1,2; Sun, Zhenan1,3; Tan, Tieniu1,3
刊名IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY
出版日期2021
卷号16页码:2776-2790
关键词Aging Faces Face recognition Facial features Generators Wavelet packets Visualization Generative adversarial networks face aging facial attribute attention mechanism wavelet packet transform
ISSN号1556-6013
DOI10.1109/TIFS.2021.3065499
通讯作者Sun, Zhenan(znsun@nlpr.ia.ac.cn)
英文摘要Face aging has received significant research attention in recent years. Although great progress has been achieved with the success of Generative Adversarial Networks (GANs) in synthesizing realistic images, most existing GAN-based face aging methods have two main problems: 1) unnatural changes of high-level semantic information due to the insufficient consideration of prior knowledge of input faces, and 2) distortions of low-level image content (e.g. modifications in age-irrelevant regions). In this article, we introduce A(3)GAN, an Attribute-Aware Attentive face aging model to address the above issues. Facial attribute vectors are regarded as the conditional information and embedded into both the generator and discriminator, encouraging synthesized faces to be faithful to attributes of corresponding inputs. To improve the visual fidelity of generation results, we leverage the attention mechanism to restrict modifications to age-related areas and preserve image details. Unlike previous works with attention modules, we introduce face parsing maps to help the generator distinguish image regions of interest and suppress attention activation elsewhere. Moreover, the wavelet packet transform is employed to capture textural features at multiple scales in the frequency space. Extensive experimental results demonstrate the effectiveness of our model in synthesizing photo-realistic aged face images and achieving state-of-the-art performance on popular datasets.
WOS关键词PERCEPTION ; MODEL
资助项目Natural Science Foundation of China[U1836217] ; Natural Science Foundation of China[62076240] ; Natural Science Foundation of China[61721004] ; Natural Science Foundation of China[61702513] ; Artificial Intelligence Research, Chinese Academy of Sciences (CAS-AIR) ; Shandong Provincial Key Research and Development Program (Major Scientific and Technological Innovation Project)[2019JZZY010119]
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:000639651900008
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
资助机构Natural Science Foundation of China ; Artificial Intelligence Research, Chinese Academy of Sciences (CAS-AIR) ; Shandong Provincial Key Research and Development Program (Major Scientific and Technological Innovation Project)
源URL[http://ir.ia.ac.cn/handle/173211/44352]  
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, Inst Automat, Ctr Res Intelligent Percept & Comp, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
2.Chinese Acad Sci, Artificial Intelligence Res, Qingdao 266300, Peoples R China
3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China
推荐引用方式
GB/T 7714		 Liu, Yunfan,Li, Qi,Sun, Zhenan,et al. A(3)GAN: An Attribute-Aware Attentive Generative Adversarial Network for Face Aging[J]. IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY,2021,16:2776-2790.
APA Liu, Yunfan,Li, Qi,Sun, Zhenan,&Tan, Tieniu.(2021).A(3)GAN: An Attribute-Aware Attentive Generative Adversarial Network for Face Aging.IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY,16,2776-2790.
MLA Liu, Yunfan,et al."A(3)GAN: An Attribute-Aware Attentive Generative Adversarial Network for Face Aging".IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY 16(2021):2776-2790.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。