Feature Agglomeration Networks for Single Stage Face Detection

Recent years have witnessed promising results of face detection using deep learning, especially for the family of region-based convolutional neural networks (R-CNN) methods and their variants. 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 framework of “Feature Agglomeration Networks” (FAN) to build a new single stage face detector, which not only achieves state-of-the-art performance but also runs efficiently. As inspired by the recent success of Feature Pyramid Networks (FPN) [15] for generic object detection, the core idea of our framework is to exploit inherent multi-scale features of a single convolutional neural network to detect faces of varied scales and characteristics 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. Unlike the existing FPN approach, we construct our FAN architecture using a new Agglomerative Connection module and further propose a Hierarchical Loss to effectively train the FAN model. We evaluate the proposed FAN detector on several public face detection benchmarks and achieved new state-of-the-art results with real-time detection speed on GPU.