Accurate Face Detection for High Performance

Abstract

Face detection has witnessed significant progress due to the advances of deep convolutional neural networks (CNNs). Its central issue in recent years is how to improve the detection performance of tiny faces. To this end, many recent works propose some specific strategies, redesign the architecture and introduce new loss functions for tiny object detection. In this report, we start from the popular one-stage RetinaNet approach and apply some recent tricks to obtain a high performance face detector. Specifically, we apply the Intersection over Union (IoU) loss function for regression, employ the two-step classification and regression for detection, revisit the data augmentation based on data-anchor-sampling for training, utilize the max-out operation for classification and use the multi-scale testing strategy for inference. As a consequence, the proposed face detection method achieves state-of-the-art performance on the most popular and challenging face detection benchmark WIDER FACE dataset.

9 pages, 3 figures, technical report

References in corpus (12)

• R-FCN: Object Detection via Region-based Fully Convolutional Networks
• Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour
• A Fast and Accurate Unconstrained Face Detector
• Face Attention Network: An Effective Face Detector for the Occluded Faces
• Face Detection through Scale-Friendly Deep Convolutional Networks
• Face Detection Using Improved Faster RCNN
• PyramidBox++: High Performance Detector for Finding Tiny Face
• Learning Better Features for Face Detection with Feature Fusion and Segmentation Supervision
• Improved Selective Refinement Network for Face Detection
• Scale-Aware Face Detection
• Feature Agglomeration Networks for Single Stage Face Detection
• Robust and High Performance Face Detector

Cited by in corpus (7)

• TinaFace: Strong but Simple Baseline for Face Detection
• Going Deeper Into Face Detection: A Survey
• RefineFace: Refinement Neural Network for High Performance Face Detection
• Mask Detection and Classification in Thermal Face Images
• Face Detection with Feature Pyramids and Landmarks
• Disentangle Your Dense Object Detector
• FOSS: Multi-Person Age Estimation with Focusing on Objects and Still Seeing Surroundings