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.
Abstract (translated)
随着深卷积神经网络(CNN)的发展,人脸检测已经取得了显著的进展。近年来,它的核心问题是如何提高微型人脸的检测性能。为此,最近的许多研究工作提出了一些具体的策略,重新设计了该体系结构,并为微小目标检测引入了新的损失函数。在本报告中,我们从流行的一阶段视网膜方法开始,并应用一些最新的技巧来获得高性能的人脸检测器。具体地说,我们采用了交叉超越联合(IOU)损失函数进行回归,采用两步分类和回归进行检测,重新访问基于数据锚采样的数据增强训练,利用最大输出操作进行分类,并采用多尺度测试策略进行推理。因此,所提出的人脸检测方法在最流行和最具挑战性的人脸检测基准更宽的人脸数据集上实现了最先进的性能。
URL
https://arxiv.org/abs/1905.01585