A Light CNN for Deep Face Representation With Noisy Labels | |
Wu, Xiang1,2,3,4![]() ![]() ![]() ![]() | |
发表期刊 | IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY
![]() |
ISSN | 1556-6013 |
2018-11-01 | |
卷号 | 13期号:11页码:2884-2896 |
通讯作者 | Sun, Zhenan(znsun@nlpr.ia.ac.cn) |
摘要 | The volume of convolutional neural network (CNN) models proposed for face recognition has been continuously growing larger to better fit the large amount of training data. When training data are obtained from the Internet, the labels are likely to be ambiguous and inaccurate. This paper presents a Light CNN framework to learn a compact embedding on the large-scale face data with massive noisy labels. First, we introduce a variation of maxout activation, called max-feature-map (MFM), into each convolutional layer of CNN. Different from maxout activation that uses many feature maps to linearly approximate an arbitrary convex activation function, MFM does so via a competitive relationship. MFM can not only separate noisy and informative signals but also play the role of feature selection between two feature maps. Second, three networks are carefully designed to obtain better performance, meanwhile, reducing the number of parameters and computational costs. Finally, a semantic bootstrapping method is proposed to make the prediction of the networks more consistent with noisy labels. Experimental results show that the proposed framework can utilize large-scale noisy data to learn a Light model that is efficient in computational costs and storage spaces. The learned single network with a 256-D representation achieves state-of-theart results on various face benchmarks without fine-tuning. |
关键词 | Convolutional neural network face recognition |
DOI | 10.1109/TIFS.2018.2833032 |
关键词[WOS] | RECOGNITION ; CLASSIFICATION |
收录类别 | SCI |
语种 | 英语 |
资助项目 | National Natural Science Foundation of China[61427811] ; National Natural Science Foundation of China[61622310] ; State Key Development Program[2016YFB1001001] ; State Key Development Program[2016YFB1001001] ; National Natural Science Foundation of China[61622310] ; National Natural Science Foundation of China[61427811] |
项目资助者 | State Key Development Program ; National Natural Science Foundation of China |
WOS研究方向 | Computer Science ; Engineering |
WOS类目 | Computer Science, Theory & Methods ; Engineering, Electrical & Electronic |
WOS记录号 | WOS:000433909100013 |
出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/21077 |
专题 | 模式识别实验室 |
通讯作者 | Sun, Zhenan |
作者单位 | 1.Chinese Acad Sci, Natl Lab Pattern Recognit, Inst Automat, Beijing 100864, Peoples R China 2.Chinese Acad Sci, Ctr Res Intelligent Percept & Comp, Inst Automat, Beijing 100864, Peoples R China 3.Chinese Acad Sci, Ctr Excellence Brain Sci & Intelligence Technol, Beijing 100864, Peoples R China 4.Univ Chinese Acad Sci, Beijing 100190, 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 | Wu, Xiang,He, Ran,Sun, Zhenan,et al. A Light CNN for Deep Face Representation With Noisy Labels[J]. IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY,2018,13(11):2884-2896. |
APA | Wu, Xiang,He, Ran,Sun, Zhenan,&Tan, Tieniu.(2018).A Light CNN for Deep Face Representation With Noisy Labels.IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY,13(11),2884-2896. |
MLA | Wu, Xiang,et al."A Light CNN for Deep Face Representation With Noisy Labels".IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY 13.11(2018):2884-2896. |
条目包含的文件 | 条目无相关文件。 |
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