Knowledge Commons of Institute of Automation，CAS
| Age Estimation Based on a Single Network with Soft Softmax of Aging Modeling | |
Zichang Tan1,2 ; Shuai Zhou1,3; Jun Wan1,2; Zhen Lei1,2; Stan Z. Li1,2
| |
| 2016 | |
| 会议名称 | 13th Asian Conference on Computer Vision |
| 会议日期 | November 20-24, 2016 |
| 会议地点 | Taipei, Taiwan |
| 摘要 | In this paper, we propose a novel approach based on a single convolutional neural network (CNN) for age estimation. In our proposed network architecture, we first model the randomness of aging with the Gaussian distribution which is used to calculate the Gaussian integral of an age interval. Then, we present a soft softmax regression function used in the network. The new function applies the aging modeling to compute the function loss. Compared with the traditional softmax function, the new function considers not only the chronological age but also the interval nearby true age. Moreover, owing to the complex of Gaussian integral in soft softmax function, a look up table is built to accelerate this process. All the integrals of age values are calculated offline in advance. We evaluate our method on two public datasets: MORPH II and Cross-Age Celebrity Dataset (CACD), and experimental results have shown that the proposed method has gained superior performances compared to the state of the art. |
| 文献类型 | 会议论文 |
| 条目标识符 | http://ir.ia.ac.cn/handle/173211/15298 |
| 专题 | 多模态人工智能系统全国重点实验室_生物识别与安全技术 |
| 通讯作者 | Jun Wan |
| 作者单位 | 1.Center for Biometrics and Security Research & National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China 2.University of Chinese Academy of Sciences 3.Faculty of Information Technology, Macau University of Science and Technology, Macau |
| 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 | Zichang Tan,Shuai Zhou,Jun Wan,et al. Age Estimation Based on a Single Network with Soft Softmax of Aging Modeling[C],2016. |
| 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 | ||
| ACCV2016_age.pdf（2273KB） | 会议论文 | 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