Deeply-learned Hybrid Representations for Facial Age Estimation | |
Zichang Tan1,2; Yang Yang1,2; Jun Wan1,2; Guodong Guo3,4; Stan Z. Li1,2,5 | |
2019-08 | |
会议日期 | 2019-8 |
会议地点 | 澳门 |
关键词 | Deep Learning, Facial Age Estimation |
DOI | https://doi.org/10.24963/ijcai.2019/492 |
英文摘要 | In this paper, we propose a novel unified network named Deep Hybrid-Aligned Architecture for facial age estimation. It contains global, local and global-local branches. They are jointly optimized and thus can capture multiple types of features with complementary information. In each branch, we employ a separate loss for each sub-network to extract the independent features and use a recurrent fusion to explore correlations among those region features. Considering that the pose variations may lead to misalignment in different regions, we design an Aligned Region Pooling operation to generate aligned region features. Moreover, a new large age dataset named Web-FaceAge owning more than 120K samples is collected under diverse scenes and spanning a large age range. Experiments on five age benchmark datasets, including Web-FaceAge, Morph, FG-NET, CACD and Chalearn LAP 2015, show that the proposed method outperforms the state-of-the-art approaches significantly. |
URL标识 | 查看原文 |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/44367] |
专题 | 自动化研究所_模式识别国家重点实验室_生物识别与安全技术研究中心 |
通讯作者 | Jun Wan |
作者单位 | 1.University of Chinese Academy of Sciences 2.Institute of Automation, Chinese Academy of Sciences (CASIA) 3.Institute of Deep Learning, Baidu Research 4.National Engineering Laboratory for Deep Learning Technology and Application 5.Faculty of Information Technology, Macau University of Science and Technology |
推荐引用方式 GB/T 7714 | Zichang Tan,Yang Yang,Jun Wan,et al. Deeply-learned Hybrid Representations for Facial Age Estimation[C]. 见:. 澳门. 2019-8. |
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