In recent years, the application of deep learning based on deep convolutional neural networks has gained great success in face detection. However, one of the remaining open challenges is the detection of small-scaled faces. The depth of the convolutional network can cause the projected feature map for small faces to be quickly shrunk, and most detection approaches with scale invariant can hardly handle less than $15\times 15$ pixel faces. To solve this problem, we propose a different scales face detector (DSFD) based on Faster R-CNN. The new network can improve the precision of face detection while performing as real-time a Faster R-CNN. First, an efficient multitask region proposal network (RPN), combined with boosting face detection, is developed to obtain the human face ROI. Setting the ROI as a constraint, an anchor is inhomogeneously produced on the top feature map by the multitask RPN. A human face proposal is extracted through the anchor combined with facial landmarks. Then, a parallel-type Fast R-CNN network is proposed based on the proposal scale. According to the different percentages they cover on the images, the proposals are assigned to three corresponding Fast R-CNN networks. The three networks are separated through the proposal scales and differ from each other in the weight of feature map concatenation. A variety of strategies is introduced in our face detection network, including multitask learning, feature pyramid, and feature concatenation. Compared to state-of-the-art face detection methods such as UnitBox, HyperFace, FastCNN, the proposed DSFD method achieves promising performance on popular benchmarks including FDDB, AFW, PASCAL faces, and WIDER FACE.

中文翻译：

---

基于更快的R-CNN的不同尺度的人脸检测

近年来，基于深度卷积神经网络的深度学习应用在面部检测中获得了巨大的成功。但是，尚待解决的挑战之一是检测小尺寸面孔。卷积网络的深度会导致小型人脸的投影特征图迅速缩小，并且大多数具有尺度不变性的检测方法几乎都无法处理少于$ 15 \乘以15 $像素的人脸。为了解决这个问题，我们提出了一种基于Faster R-CNN的不同尺度的人脸检测器（DSFD）。新网络可以实时执行Faster R-CNN，从而提高人脸检测的精度。首先，开发了一种有效的多任务区域提议网络（RPN），并结合了增强的人脸检测功能，以获得人脸ROI。将ROI设置为约束条件，多任务RPN在顶部要素地图上不均匀地生成锚点。通过结合了地标的锚点提取人脸提议。然后，基于提议规模，提出了一种并行型快速R-CNN网络。根据它们在图像上所占的百分比不同，将提案分配给三个相应的Fast R-CNN网络。这三个网络通过提议比例尺分开，并且在特征图串联的权重方面彼此不同。我们的面部检测网络引入了多种策略，包括多任务学习，特征金字塔和特征串联。与UnitBox，HyperFace，FastCNN等最新的人脸检测方法相比，拟议的DSFD方法在包括FDDB，AFW，