S$^3$FD: Single Shot Scale-invariant Face Detector

17 Aug 2017  ·  Shifeng Zhang, Xiangyu Zhu, Zhen Lei, Hailin Shi, Xiaobo Wang, Stan Z. Li ·

This paper presents a real-time face detector, named Single Shot Scale-invariant Face Detector (S$^3$FD), which performs superiorly on various scales of faces with a single deep neural network, especially for small faces. Specifically, we try to solve the common problem that anchor-based detectors deteriorate dramatically as the objects become smaller. We make contributions in the following three aspects: 1) proposing a scale-equitable face detection framework to handle different scales of faces well. We tile anchors on a wide range of layers to ensure that all scales of faces have enough features for detection. Besides, we design anchor scales based on the effective receptive field and a proposed equal proportion interval principle; 2) improving the recall rate of small faces by a scale compensation anchor matching strategy; 3) reducing the false positive rate of small faces via a max-out background label. As a consequence, our method achieves state-of-the-art detection performance on all the common face detection benchmarks, including the AFW, PASCAL face, FDDB and WIDER FACE datasets, and can run at 36 FPS on a Nvidia Titan X (Pascal) for VGA-resolution images.

PDF Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Face Detection FDDB S3FD AP 0.983 # 5
Face Detection PASCAL Face S3FD AP 0.9849 # 2
Face Detection WIDER Face (Easy) S3FD(F+S+M) AP 0.937 # 22
Face Detection WIDER Face (Hard) S3FD(F+S+M) AP 0.852 # 22
Face Detection WIDER Face (Medium) S3FD(F+S+M) AP 0.924 # 22

Methods


No methods listed for this paper. Add relevant methods here