Affordable Access

Access to the full text

Single-Shot Scale-Aware Network for Real-Time Face Detection

Authors
  • Zhang, Shifeng1, 2
  • Wen, Longyin3
  • Shi, Hailin4
  • Lei, Zhen1, 2
  • Lyu, Siwei5
  • Li, Stan Z.1, 2
  • 1 Chinese Academy of Sciences, CBSR & NLPR, Institute of Automation, Beijing, China , Beijing (China)
  • 2 University of Chinese Academy of Sciences, Beijing, China , Beijing (China)
  • 3 JD Digits, Mountain View, CA, USA , Mountain View (United States)
  • 4 JD AI Research, Beijing, China , Beijing (China)
  • 5 University at Albany, SUNY, Computer Science Department, Albany, NY, USA , Albany (United States)
Type
Published Article
Journal
International Journal of Computer Vision
Publisher
Springer-Verlag
Publication Date
Feb 19, 2019
Volume
127
Issue
6-7
Pages
537–559
Identifiers
DOI: 10.1007/s11263-019-01159-3
Source
Springer Nature
Keywords
License
Yellow

Abstract

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.

Report this publication

Statistics

Seen <100 times