Detecting Faces Using Region-based Fully Convolutional Networks
This work addresses face detection for computer vision applications, representing an incremental improvement over existing region-based detectors.
The authors tackled face detection by proposing Face R-FCN, a region-based fully convolutional network, which improved accuracy and computational efficiency over previous methods, achieving superior performance on benchmarks like FDDB and WIDER FACE.
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.