Memory-Modulated Transformer Network for Heterogeneous Face Recognition
文献类型：期刊论文
| ; | |
| 作者 | Luo, Mandi1,2,3 ; Wu, Haoxue1,2; Huang, Huaibo1,2,3; He, Weizan4; He, Ran1,2,3
|
| 刊名 | IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY
 ; IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY
|
| 出版日期 | 2022 ; 2022 |
| 卷号 | 17页码:2095-2109 |
| ISSN号 | 1556-6013 ; 1556-6013 |
| 关键词 | Face recognition Face recognition Task analysis Transformers Encoding Feature extraction Image recognition Memory modules Heterogeneous face recognition style transformer memory network Task analysis Transformers Encoding Feature extraction Image recognition Memory modules Heterogeneous face recognition style transformer memory network |
| DOI | 10.1109/TIFS.2022.3177960 ; 10.1109/TIFS.2022.3177960 |
| 通讯作者 | He, Ran(rhe@nlpria.ac.cn) ; He, Ran(rhe@nlpria.ac.cn) |
| 英文摘要 | Heterogeneous face recognition (HFR) aims at matching face images across different domains. It is challenging due to the severe domain discrepancies and overfitting caused by small training datasets. Some researchers apply a "recognition via generation" strategy and propose to solve the problem by translating images from a given domain into the visual domain. However, in many HFR tasks such as near-infrablack HFR, there is no paiblack data, which makes it an unsupervised generation. Pose variations, background differences, and many other factors present challenges. Moreover, the generated results lack diversity since many previous works regard this image translation as a "one-to-one" generation task. Considering the information deficiency in the input images, we propose to formulate this image translation process as a "one-to-many" generation problem. Specifically, we introduce reference images to guide the generation process. We propose a memory module to explore the prototypical style patterns of the reference domain. After self-supervised updating, the memory items are attentively aggregated to represent the style information. Moreover, to subtly fuse the contents of input images with the style of reference images, we propose a novel style transformer module. Specifically, we crop the encoded input and reference feature maps into patches, and use the style transformer to establish long-range dependencies between the input and reference patches. Thus, the style of every input patch is transferblack based on those of the most relevant reference patches. Extensive experiments on multiple datasets for various HFR tasks, including NIR-VIS, thermal-VIS, sketch-photo, and gray-RGB, are conducted. The robustness and effectiveness of the proposed MMTN are demonstrated both quantitatively and qualitatively.; Heterogeneous face recognition (HFR) aims at matching face images across different domains. It is challenging due to the severe domain discrepancies and overfitting caused by small training datasets. Some researchers apply a "recognition via generation" strategy and propose to solve the problem by translating images from a given domain into the visual domain. However, in many HFR tasks such as near-infrablack HFR, there is no paiblack data, which makes it an unsupervised generation. Pose variations, background differences, and many other factors present challenges. Moreover, the generated results lack diversity since many previous works regard this image translation as a "one-to-one" generation task. Considering the information deficiency in the input images, we propose to formulate this image translation process as a "one-to-many" generation problem. Specifically, we introduce reference images to guide the generation process. We propose a memory module to explore the prototypical style patterns of the reference domain. After self-supervised updating, the memory items are attentively aggregated to represent the style information. Moreover, to subtly fuse the contents of input images with the style of reference images, we propose a novel style transformer module. Specifically, we crop the encoded input and reference feature maps into patches, and use the style transformer to establish long-range dependencies between the input and reference patches. Thus, the style of every input patch is transferblack based on those of the most relevant reference patches. Extensive experiments on multiple datasets for various HFR tasks, including NIR-VIS, thermal-VIS, sketch-photo, and gray-RGB, are conducted. The robustness and effectiveness of the proposed MMTN are demonstrated both quantitatively and qualitatively. |
| WOS关键词 | SPECTRAL REGRESSION ; SPECTRAL REGRESSION ; DICTIONARY ; RANKING ; DICTIONARY ; RANKING |
| 资助项目 | National Natural Science Foundation of China[U21B2045] ; National Natural Science Foundation of China[U21B2045] ; National Natural Science Foundation of China[U20A20223] ; Youth Innovation Promotion Association Chinese Academy of Sciences (CAS)[Y201929] ; National Natural Science Foundation of China[U20A20223] ; Youth Innovation Promotion Association Chinese Academy of Sciences (CAS)[Y201929] |
| WOS研究方向 | Computer Science ; Computer Science ; Engineering ; Engineering |
| 语种 | 英语 ; 英语 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC ; IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| WOS记录号 | WOS:000812529100004 ; WOS:000812529100004 |
| 资助机构 | National Natural Science Foundation of China ; National Natural Science Foundation of China ; Youth Innovation Promotion Association Chinese Academy of Sciences (CAS) ; Youth Innovation Promotion Association Chinese Academy of Sciences (CAS) |
| 源URL | [http://ir.ia.ac.cn/handle/173211/49231]  |
| 专题 | 自动化研究所_智能感知与计算研究中心 |
| 通讯作者 | He, Ran |
| 作者单位 | 1.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 101408, Peoples R China 2.Chinese Acad Sci, Ctr Res Intelligent Percept & Comp, Inst Automat, Natl Lab Pattern Recognit, Beijing 100049, Peoples R China 3.CAS Ctr Excellence Brain Sci & Intelligence Techn, Beijing 100190, Peoples R China 4.Beijing Inst Technol, Sch Automat, Beijing 100811, Peoples R China |
| 推荐引用方式 GB/T 7714 | Luo, Mandi,Wu, Haoxue,Huang, Huaibo,et al. Memory-Modulated Transformer Network for Heterogeneous Face Recognition, Memory-Modulated Transformer Network for Heterogeneous Face Recognition[J]. IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY,2022, 2022,17, 17:2095-2109, 2095-2109. |
| APA | Luo, Mandi,Wu, Haoxue,Huang, Huaibo,He, Weizan,&He, Ran.(2022).Memory-Modulated Transformer Network for Heterogeneous Face Recognition.IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY,17,2095-2109. |
| MLA | Luo, Mandi,et al."Memory-Modulated Transformer Network for Heterogeneous Face Recognition".IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY 17(2022):2095-2109. |
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。