中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
  5. 生物识别与安全技术研究中心
Single-Shot Scale-Aware Network for Real-Time Face Detection

文献类型：期刊论文

作者Zhang, Shifeng1,2,3; Wen, Longyin4; Shi, Hailin5; Lei, Zhen1,2,3; Lyu, Siwei6; Li, Stan Z.1,2,3
刊名INTERNATIONAL JOURNAL OF COMPUTER VISION
出版日期2019-06-01
卷号127期号:6-7页码:537-559
ISSN号0920-5691
关键词Face detection Single-shot Scale-aware Class imbalance
DOI10.1007/s11263-019-01159-3
通讯作者Lei, Zhen(zlei@nlpr.ia.ac.cn)
英文摘要In this work, we describe a single-shot scale-aware convolutional neural network based face detector (SFDet). In comparison with the state-of-the-art anchor-based face detection methods, the main advantages of our method are summarized in four aspects. (1) We propose a scale-aware detection network using a wide scale range of layers associated with appropriate scales of anchors to handle faces with various scales, and describe a new equal density principle to ensure anchors with different scales to be evenly distributed on the image. (2) To improve the recall rates of faces with certain scales (e.g., the scales of the faces are quite different from the scales of designed anchors), we design a new anchor matching strategy with scale compensation. (3) We introduce an IoU-aware weighting scheme for each training sample in classification loss calculation to encode samples accurately in training process. (4) Considering the class imbalance issue, a max-out background strategy is used to reduce false positives. Several experiments are conducted on public challenging face detection datasets, i.e., WIDER FACE, AFW, PASCAL Face, FDDB, and MAFA, to demonstrate that the proposed method achieves the state-of-the-art results and runs at 82.1 FPS for the VGA-resolution images.
资助项目Chinese National Natural Science Foundation[61876178] ; Chinese National Natural Science Foundation[61473291] ; Chinese National Natural Science Foundation[61806196] ; National Key Research and Development Plan[2016YFC0801002] ; JD Grapevine Plan ; Authen Metric RD Funds
WOS研究方向Computer Science
语种英语
出版者SPRINGER
WOS记录号WOS:000468525900002
资助机构Chinese National Natural Science Foundation ; National Key Research and Development Plan ; JD Grapevine Plan ; Authen Metric RD Funds
源URL[http://ir.ia.ac.cn/handle/173211/24230]  
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Lei, Zhen
作者单位1.Chinese Acad Sci, Inst Automat, CBSR, Beijing, Peoples R China
2.Chinese Acad Sci, Inst Automat, NLPR, Beijing, Peoples R China
3.Univ Chinese Acad Sci, Beijing, Peoples R China
4.JD Digits, Mountain View, CA USA
5.JD AI Res, Beijing, Peoples R China
6.SUNY Albany, Dept Comp Sci, Albany, NY 12222 USA
推荐引用方式
GB/T 7714		 Zhang, Shifeng,Wen, Longyin,Shi, Hailin,et al. Single-Shot Scale-Aware Network for Real-Time Face Detection[J]. INTERNATIONAL JOURNAL OF COMPUTER VISION,2019,127(6-7):537-559.
APA Zhang, Shifeng,Wen, Longyin,Shi, Hailin,Lei, Zhen,Lyu, Siwei,&Li, Stan Z..(2019).Single-Shot Scale-Aware Network for Real-Time Face Detection.INTERNATIONAL JOURNAL OF COMPUTER VISION,127(6-7),537-559.
MLA Zhang, Shifeng,et al."Single-Shot Scale-Aware Network for Real-Time Face Detection".INTERNATIONAL JOURNAL OF COMPUTER VISION 127.6-7(2019):537-559.

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。