EMface: Detecting Hard Faces by Exploring Receptive Field Pyraminds
This addresses a key challenge in face detection for computer vision applications, though it appears incremental as it builds on existing feature pyramid approaches.
The paper tackles scale variation in face detection by proposing a receptive field pyramids method to enhance feature pyramids, achieving state-of-the-art performance and significantly accelerating inference on benchmark datasets like WIDER FACE and UFDD.
Scale variation is one of the most challenging problems in face detection. Modern face detectors employ feature pyramids to deal with scale variation. However, it might break the feature consistency across different scales of faces. In this paper, we propose a simple yet effective method named the receptive field pyramids (RFP) method to enhance the representation ability of feature pyramids. It can learn different receptive fields in each feature map adaptively based on the varying scales of detected faces. Empirical results on two face detection benchmark datasets, i.e., WIDER FACE and UFDD, demonstrate that our proposed method can accelerate the inference rate significantly while achieving state-of-the-art performance. The source code of our method is available at \url{https://github.com/emdata-ailab/EMface}.