Selective Refinement Network for High Performance Face Detection

Authors

  • Cheng Chi Chinese Academy of Sciences
  • Shifeng Zhang Chinese Academy of Sciences
  • Junliang Xing Chinese Academy of Sciences
  • Zhen Lei Chinese Academy of Sciences
  • Stan Z. Li Chinese Academy of Sciences
  • Xudong Zou Chinese Academy of Sciences

DOI:

https://doi.org/10.1609/aaai.v33i01.33018231

Abstract

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 twostep 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.

Downloads

Published

2019-07-17

How to Cite

Chi, C., Zhang, S., Xing, J., Lei, Z., Li, S. Z., & Zou, X. (2019). Selective Refinement Network for High Performance Face Detection. Proceedings of the AAAI Conference on Artificial Intelligence, 33(01), 8231-8238. https://doi.org/10.1609/aaai.v33i01.33018231

Issue

Section

AAAI Technical Track: Vision