Selective Refinement Network for High Performance Face Detection

TL;DR

The paper introduces the Selective Refinement Network (SRN), a novel face detector that improves accuracy and reduces false positives, especially for tiny faces, by employing two-step classification and regression modules with receptive field enhancement.

Contribution

The paper proposes the SRN with selective two-step classification and regression modules, and a receptive field enhancement block, achieving state-of-the-art face detection performance.

Findings

Achieves state-of-the-art results on multiple face detection benchmarks.

Effectively reduces false positives and improves localization accuracy.

Performs well on challenging tiny face detection scenarios.

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 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.