Deep Label Refnement for Age Estimation | |
Li PP(李佩佩) | |
刊名 | Pattern Recognition |
2020 | |
卷号 | 100期号:-页码:107178 |
关键词 | age estimation |
英文摘要 | Age estimation of unknown persons is a challenging pattern analysis task due to the lacking of training data and various aging mechanisms for different individuals. Label distribution learning-based methods usually make distribution assumptions to simplify age estimation. However, since humans with different genders, races and/or any other situations may influence their facial aging appearances, age label distributions are often complicated and difficult to be modeled in a parameter way. In this paper, we propose a Label Refinery Network (LRN) with two concurrent refinery processes: label distribution refinery and slack regression refinery. Label refinery network aims to learn age label distributions progressively in an iterative manner. In this way, we can adaptively obtain the specific age label distributions for different facial images without making strong assumptions of fixed distribution formulations. To further utilize the correlations among age labels, we accordingly propose a slack regression refinery to convert the age label regression into the age interval regression. Extensive experiments on three popular datasets, including Morph, ChaLearn15 and MegaAge-Asian demonstrate the superiority of our method. |
语种 | 英语 |
内容类型 | 期刊论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/44788] |
专题 | 自动化研究所_智能感知与计算研究中心 |
作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Li PP. Deep Label Refnement for Age Estimation[J]. Pattern Recognition,2020,100(-):107178. |
APA | Li PP.(2020).Deep Label Refnement for Age Estimation.Pattern Recognition,100(-),107178. |
MLA | Li PP."Deep Label Refnement for Age Estimation".Pattern Recognition 100.-(2020):107178. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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