Knowledge Commons of Institute of Automation,CAS
FedFV: federated face verification via equivalent class embeddings | |
Liu, Lingyun1,2,3; Zhang, Yifan1,2; Gao, Haoyuan1,2,4; Yu, Xingtao5; Cheng, Jian1,2 | |
发表期刊 | MULTIMEDIA SYSTEMS |
ISSN | 0942-4962 |
2022-04-22 | |
页码 | 11 |
摘要 | Face verification models based on centralized training on large face datasets have achieved excellent performance on various test benchmarks. However, due to the increasingly sophisticated privacy protection law, centrally collecting large amount of face images becomes more difficult. We consider learning a face verification model in the federated setting, where each client has access to the face images of only one class and class embeddings cannot be shared to other clients because of data privacy. In this paper, we propose Federated face verification (FedFV), in which server transfers some equivalent class embeddings to clients so that the clients' class embeddings can be separated far away from each other. We show that our proposed method FedFV outperforms the existing approaches in several face verification benchmarks. |
关键词 | Equivalent class embeddings Federated learning Face recognition Deep learning |
DOI | 10.1007/s00530-022-00927-5 |
收录类别 | SCI |
语种 | 英语 |
资助项目 | Strategic Priority Research Program of Chinese Academy of Sciences[XDA27040300] ; Jiangsu Key Research and Development Plan ; NSFC[61906195] ; NSFC[61876182] |
项目资助者 | Strategic Priority Research Program of Chinese Academy of Sciences ; Jiangsu Key Research and Development Plan ; NSFC |
WOS研究方向 | Computer Science |
WOS类目 | Computer Science, Information Systems ; Computer Science, Theory & Methods |
WOS记录号 | WOS:000785587500001 |
出版者 | SPRINGER |
七大方向——子方向分类 | 图像视频处理与分析 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/48308 |
专题 | 复杂系统认知与决策实验室_高效智能计算与学习 |
通讯作者 | Zhang, Yifan |
作者单位 | 1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 2.Nanjing Artificial Intelligence Res IA, Nanjing 211135, Jiangsu, Peoples R China 3.Univ Chinese Acad Sci, Sch Future Technol, Beijing 100049, Peoples R China 4.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 5.Nanjing Chi Lin Innovat Pk, Adm Comm, Nanjing 211135, Jiangsu, Peoples R China |
第一作者单位 | 模式识别国家重点实验室 |
通讯作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Liu, Lingyun,Zhang, Yifan,Gao, Haoyuan,et al. FedFV: federated face verification via equivalent class embeddings[J]. MULTIMEDIA SYSTEMS,2022:11. |
APA | Liu, Lingyun,Zhang, Yifan,Gao, Haoyuan,Yu, Xingtao,&Cheng, Jian.(2022).FedFV: federated face verification via equivalent class embeddings.MULTIMEDIA SYSTEMS,11. |
MLA | Liu, Lingyun,et al."FedFV: federated face verification via equivalent class embeddings".MULTIMEDIA SYSTEMS (2022):11. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
FedFV.pdf(1435KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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。
修改评论