DSFD: Dual Shot Face Detector

CVPR 2019 Jian LiYabiao WangChangan WangYing TaiJianjun QianJian YangChengjie WangJilin LiFeiyue Huang

In this paper, we propose a novel face detection network with three novel contributions that address three key aspects of face detection, including better feature learning, progressive loss design and anchor assign based data augmentation, respectively. First, we propose a Feature Enhance Module (FEM) for enhancing the original feature maps to extend the single shot detector to dual shot detector... (read more)

PDF Abstract

Evaluation results from the paper

Task Dataset Model Metric name Metric value Global rank Compare
Face Detection FDDB DSFD AP 0.991 # 1
Face Detection WIDER Face (Easy) DSFD AP 0.960 # 2
Face Detection WIDER Face (Hard) DSFD AP 0.900 # 3
Face Detection WIDER Face (Medium) DSFD AP 0.953 # 2