Selective Refinement Network for High Performance Face Detection

7 Sep 2018  ·  Cheng Chi, Shifeng Zhang, Junliang Xing, Zhen Lei, Stan Z. Li, Xudong Zou ·

High performance face detection remains a very challenging problem, especially when there exists many tiny faces. This paper presents a novel single-shot face detector, named Selective Refinement Network (SRN), which introduces novel two-step classification and regression operations selectively into an anchor-based face detector to reduce false positives and improve location accuracy simultaneously. In particular, the SRN consists of two modules: the Selective Two-step Classification (STC) module and the Selective Two-step Regression (STR) module. The STC aims to filter out most simple negative anchors from low level detection layers to reduce the search space for the subsequent classifier, while the STR is designed to coarsely adjust the locations and sizes of anchors from high level detection layers to provide better initialization for the subsequent regressor. Moreover, we design a Receptive Field Enhancement (RFE) block to provide more diverse receptive field, which helps to better capture faces in some extreme poses. As a consequence, the proposed SRN detector achieves state-of-the-art performance on all the widely used face detection benchmarks, including AFW, PASCAL face, FDDB, and WIDER FACE datasets. Codes will be released to facilitate further studies on the face detection problem.

PDF Abstract

Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Face Detection Annotated Faces in the Wild SRN AP 0.9987 # 1
Face Detection FDDB SRN AP 0.988 # 3
Face Detection PASCAL Face SRN AP 0.9909 # 1
Face Detection WIDER Face (Easy) SRN AP 0.959 # 11
Face Detection WIDER Face (Hard) SRN AP 0.896 # 9
Face Detection WIDER Face (Medium) SRN AP 0.948 # 11


No methods listed for this paper. Add relevant methods here