Learning Face Representation from Scratch
Yi D(易东); Lei Z(雷震); Liao SC(廖胜才); Li ZQ(李子青)
2014
发表期刊arXiv preprint
期号11页码:1
摘要Pushing by big data and deep convolutional neural network (CNN), the
performance of face recognition is becoming comparable to human. Using private large
scale training datasets, several groups achieve very high performance on LFW, ie, 97% to
99%. While there are many open source implementations of CNN, none of large scale face
dataset is publicly available. The current situation in the field of face recognition is that data
is more important than algorithm. To solve this problem, this paper proposes a semi-
automatical way to collect face images from Internet and builds a large scale dataset
containing about 10,000 subjects and 500,000 images, called CASIAWebFace. Based on
the database, we use a 11-layer CNN to learn discriminative representation and obtain state-
of-theart accuracy on LFW and YTF.
关键词人脸识别
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/20605
专题模式识别国家重点实验室_生物识别与安全技术研究
推荐引用方式
GB/T 7714
Yi D,Lei Z,Liao SC,et al. Learning Face Representation from Scratch[J]. arXiv preprint,2014(11):1.
APA Yi D,Lei Z,Liao SC,&Li ZQ.(2014).Learning Face Representation from Scratch.arXiv preprint(11),1.
MLA Yi D,et al."Learning Face Representation from Scratch".arXiv preprint .11(2014):1.
条目包含的文件
条目无相关文件。
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Yi D(易东)]的文章
[Lei Z(雷震)]的文章
[Liao SC(廖胜才)]的文章
百度学术
百度学术中相似的文章
[Yi D(易东)]的文章
[Lei Z(雷震)]的文章
[Liao SC(廖胜才)]的文章
必应学术
必应学术中相似的文章
[Yi D(易东)]的文章
[Lei Z(雷震)]的文章
[Liao SC(廖胜才)]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

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。