D2C: Deep cumulatively and comparatively learning for human age estimation
文献类型:期刊论文
作者 | Li, Kai1![]() ![]() ![]() |
刊名 | PATTERN RECOGNITION
![]() |
出版日期 | 2017-06-01 |
卷号 | 66期号:0页码:95-105 |
关键词 | Age Estimation Deep Learning Convolutional Neural Network |
DOI | 10.1016/j.patcog.2017.01.007 |
文献子类 | Article |
英文摘要 | Age estimation from face images is an important yet difficult task in computer vision. Its main difficulty lies in how to design aging features that remain discriminative in spite of large facial appearance variations. Meanwhile, due to the difficulty of collecting and labeling datasets that contain sufficient samples for all possible ages, the age distributions of most benchmark datasets are often imbalanced, which makes this problem more challenge. In this work, we try to solve these difficulties by means of the mainstream deep learning techniques. Specifically, we use a convolutional neural network which can learn discriminative aging features from raw face images without any handcrafting. To combat the sample imbalance problem, we propose a novel cumulative hidden layer which is supervised by a point-wise cumulative signal. With this cumulative hidden layer, our model is learnt indirectly using faces with neighbouring ages and thus alleviate the sample imbalance problem. In order to learn more effective aging features, we further propose a comparative ranking layer which is supervised by a pair-wise comparative signal. This comparative ranking layer facilitates aging feature learning and improves the performance of the main age estimation task. In addition, since one face can be included in many different training pairs, we can make full use of the limited training data. It is noted that both of these two novel layers are differentiable, so our model is end-to-end trainable. Extensive experiments on the two of the largest benchmark datasets show that our deep age estimation model gains notable advantage on accuracy when compared against existing methods. |
WOS关键词 | FACE IMAGES ; DIMENSIONALITY ; REGRESSION |
WOS研究方向 | Computer Science ; Engineering |
语种 | 英语 |
WOS记录号 | WOS:000397371800011 |
资助机构 | 973 basic research program of China(2014CB349303) ; Natural Science Foundation of China(61472421 ; CAS(XDB02070003) ; 61672519 ; U1636218 ; 61303178) |
源URL | [http://ir.ia.ac.cn/handle/173211/15080] ![]() |
专题 | 自动化研究所_模式识别国家重点实验室_视频内容安全团队 |
作者单位 | 1.National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, PR China 2.CAS Center for Excellence in Brain Science and Intelligence Technology, Institute of Automation, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing 100190, PR China 3.Department of Computer Science and Information Systems, Birkbeck College, London WC1E 7HX, United Kingdom |
推荐引用方式 GB/T 7714 | Li, Kai,Xing, Junliang,Hu, Weiming,et al. D2C: Deep cumulatively and comparatively learning for human age estimation[J]. PATTERN RECOGNITION,2017,66(0):95-105. |
APA | Li, Kai,Xing, Junliang,Hu, Weiming,&Maybank, Stephen J..(2017).D2C: Deep cumulatively and comparatively learning for human age estimation.PATTERN RECOGNITION,66(0),95-105. |
MLA | Li, Kai,et al."D2C: Deep cumulatively and comparatively learning for human age estimation".PATTERN RECOGNITION 66.0(2017):95-105. |
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。