Recent years have witnessed promising results of face detection using deep
learning. Despite making remarkable progresses, face detection in the wild
remains an open research challenge especially when detecting faces at vastly
different scales and characteristics. In this paper, we propose a novel simple
yet effective framework of "Feature Agglomeration Networks" (FANet) to build a
new single stage face detector, which not only achieves state-of-the-art
performance but also runs efficiently. As inspired by Feature Pyramid Networks
(FPN), the key idea of our framework is to exploit inherent multi-scale
features of a single convolutional neural network by aggregating higher-level
semantic feature maps of different scales as contextual cues to augment
lower-level feature maps via a hierarchical agglomeration manner at marginal
extra computation cost. We further propose a Hierarchical Loss to effectively
train the FANet model. We evaluate the proposed FANet detector on several
public face detection benchmarks, including PASCAL face, FDDB and WIDER FACE
datasets and achieved state-of-the-art results. Our detector can run in real
time for VGA-resolution images on GPU.

本文中，我们提出了一种名为 FANet 的新型单阶段人脸检测器，它不仅实现了最新的性能，而且运行效率高。此外，我们还提出了一种分层损失来有效地训练 FANet 模型，并在几个公共人脸检测基准测试集上评估了所提出的 FANet 检测器，包括 PASCAL face、FDDB 和 WIDER FACE 数据集，在这些基准测试集上都获得了最新的结果。