Detecting Faces Using Region-based Fully Convolutional Networks

TL;DR

This paper introduces Face R-FCN, a fully convolutional region-based face detector that improves accuracy and efficiency using ResNet backbone, multi-scale training, and hard example mining, outperforming existing methods on FDDB and WIDER FACE.

Contribution

The paper presents a novel fully convolutional face detection method based on R-FCN with ResNet backbone, incorporating new techniques for enhanced accuracy and efficiency.

Findings

Outperforms state-of-the-art on FDDB and WIDER FACE benchmarks.

Achieves higher detection accuracy with improved computational efficiency.

Utilizes multi-scale training and hard example mining for better robustness.

Abstract

Face detection has achieved great success using the region-based methods. In this report, we propose a region-based face detector applying deep networks in a fully convolutional fashion, named Face R-FCN. Based on Region-based Fully Convolutional Networks (R-FCN), our face detector is more accurate and computational efficient compared with the previous R-CNN based face detectors. In our approach, we adopt the fully convolutional Residual Network (ResNet) as the backbone network. Particularly, We exploit several new techniques including position-sensitive average pooling, multi-scale training and testing and on-line hard example mining strategy to improve the detection accuracy. Over two most popular and challenging face detection benchmarks, FDDB and WIDER FACE, Face R-FCN achieves superior performance over state-of-the-arts.