Task-Oriented Feature-Fused Network With Multivariate Dataset for Joint Face Analysis
Lin, Xuxin1,2,3; Wan, Jun1,2; Xie, Yiliang3; Zhang, Shifeng1,2; Lin, Chi4; Liang, Yanyan3; Guo, Guodong5,6; Li, Stan Z.1,2
发表期刊IEEE TRANSACTIONS ON CYBERNETICS
ISSN2168-2267
2020-03-01
卷号50期号:3页码:1292-1305
摘要

Deep multitask learning for face analysis has received increasing attentions. From literature, most existing methods focus on optimizing a main task by jointly learning several auxiliary tasks. It is challenging to consider the performance of each task in a multitask framework due to the following reasons: 1) different face tasks usually rely on different levels of semantic features; 2) each task has different learning convergence rate, which could affect the whole performance when joint training; and 3) multitask model needs rich label information for efficient training, but existing facial datasets provide limited annotations. To address these issues, we propose a task-oriented feature-fused network (TFN) for simultaneously solving face detection, landmark localization, and attribute analysis. In this network, a task-oriented feature-fused block is designed to learn task-specific feature combinations; then, an alternative multitask training scheme is presented to optimize each task with considering of their different learning capacities. We also present a large-scale face dataset called JFA in support of proposed method, which provides multivariate labels, including face bounding box, 68 facial landmarks, and 3 attribute labels (i.e., apparent age, gender, and ethnicity). The experimental results suggest that the TFN outperforms several multitask models on the JFA dataset. Furthermore, our approach achieves competitive performances on WIDER FACE and 300W dataset, and obtains state-of-the-art results for gender recognition on the MORPH II dataset.

关键词Face Task analysis Training Face recognition Facial features Pipelines Attribute analysis face analysis face detection landmark localization multitask learning
DOI10.1109/TCYB.2019.2917049
收录类别SCI
语种英语
资助项目Science and Technology Development Fund of Macau[008/2019/A1] ; Science and Technology Development Fund of Macau[0025/2018/A1] ; Chinese National Natural Science Foundation[61876179] ; Chinese National Natural Science Foundation[61872367] ; Science and Technology Development Fund of Macau[152/2017/A] ; National Key Research and Development Plan[2016YFC0801002] ; National Key Research and Development Plan[2016YFC0801002] ; Science and Technology Development Fund of Macau[152/2017/A] ; Chinese National Natural Science Foundation[61872367] ; Chinese National Natural Science Foundation[61876179] ; Science and Technology Development Fund of Macau[0025/2018/A1] ; Science and Technology Development Fund of Macau[008/2019/A1]
WOS研究方向Automation & Control Systems ; Computer Science
WOS类目Automation & Control Systems ; Computer Science, Artificial Intelligence ; Computer Science, Cybernetics
WOS记录号WOS:000510941100035
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
七大方向——子方向分类图像视频处理与分析
引用统计
被引频次:7[WOS]   [WOS记录]     [WOS相关记录]
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/28595
专题模式识别国家重点实验室_生物识别与安全技术
通讯作者Liang, Yanyan
作者单位1.Chinese Acad Sci, Inst Automat, Ctr Biometr & Secur Res, Beijing 100190, Peoples R China
2.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
3.Macau Univ Sci & Technol, Fac Informat Technol, Macau 999078, Peoples R China
4.Univ Southern Calif, USC Viterbi Sch Engn, Los Angeles, CA 90089 USA
5.Baidu Res, Inst Deep Learning, Beijing 100193, Peoples R China
6.Baidu Res, Natl Engn Lab Deep Learning Technol & Applicat, Beijing 100193, Peoples R China
第一作者单位中国科学院自动化研究所;  模式识别国家重点实验室
推荐引用方式
GB/T 7714
Lin, Xuxin,Wan, Jun,Xie, Yiliang,et al. Task-Oriented Feature-Fused Network With Multivariate Dataset for Joint Face Analysis[J]. IEEE TRANSACTIONS ON CYBERNETICS,2020,50(3):1292-1305.
APA Lin, Xuxin.,Wan, Jun.,Xie, Yiliang.,Zhang, Shifeng.,Lin, Chi.,...&Li, Stan Z..(2020).Task-Oriented Feature-Fused Network With Multivariate Dataset for Joint Face Analysis.IEEE TRANSACTIONS ON CYBERNETICS,50(3),1292-1305.
MLA Lin, Xuxin,et al."Task-Oriented Feature-Fused Network With Multivariate Dataset for Joint Face Analysis".IEEE TRANSACTIONS ON CYBERNETICS 50.3(2020):1292-1305.
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
Task-Oriented Featur(3737KB)期刊论文作者接受稿开放获取CC BY-NC-SA浏览 下载
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
[Lin, Xuxin]的文章
[Wan, Jun]的文章
[Xie, Yiliang]的文章
百度学术
百度学术中相似的文章
[Lin, Xuxin]的文章
[Wan, Jun]的文章
[Xie, Yiliang]的文章
必应学术
必应学术中相似的文章
[Lin, Xuxin]的文章
[Wan, Jun]的文章
[Xie, Yiliang]的文章
相关权益政策
暂无数据
收藏/分享
文件名: Task-Oriented Feature-Fused Network With Multivariate Dataset for Joint Face Analysis.pdf
格式: Adobe PDF
此文件暂不支持浏览
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。