PyramidBox: A Context-assisted Single Shot Face Detector

Abstract

Face detection has been well studied for many years and one of remaining challenges is to detect small, blurred and partially occluded faces in uncontrolled environment. This paper proposes a novel context-assisted single shot face detector, named \emph{PyramidBox} to handle the hard face detection problem. Observing the importance of the context, we improve the utilization of contextual information in the following three aspects. First, we design a novel context anchor to supervise high-level contextual feature learning by a semi-supervised method, which we call it PyramidAnchors. Second, we propose the Low-level Feature Pyramid Network to combine adequate high-level context semantic feature and Low-level facial feature together, which also allows the PyramidBox to predict faces of all scales in a single shot. Third, we introduce a context-sensitive structure to increase the capacity of prediction network to improve the final accuracy of output. In addition, we use the method of Data-anchor-sampling to augment the training samples across different scales, which increases the diversity of training data for smaller faces. By exploiting the value of context, PyramidBox achieves superior performance among the state-of-the-art over the two common face detection benchmarks, FDDB and WIDER FACE. Our code is available in PaddlePaddle: \href{https://github.com/PaddlePaddle/models/tree/develop/fluid/face_detection}{\url{https://github.com/PaddlePaddle/models/tree/develop/fluid/face_detection}}.

arXiv comment21 pages, 12 figures

References in corpus (5)

• Focal Loss for Dense Object Detection
• A Fast and Accurate Unconstrained Face Detector
• Single-Shot Refinement Neural Network for Object Detection
• From Facial Parts Responses to Face Detection: A Deep Learning Approach
• Occlusion Coherence: Detecting and Localizing Occluded Faces

Cited by in corpus (11)

• SiamFC++: Towards Robust and Accurate Visual Tracking with Target Estimation Guidelines
• Learning Better Features for Face Detection with Feature Fusion and Segmentation Supervision
• Improved Selective Refinement Network for Face Detection
• iQIYI-VID: A Large Dataset for Multi-modal Person Identification
• Selective Refinement Network for High Performance Face Detection
• A Survey on Deep Domain Adaptation and Tiny Object Detection Challenges, Techniques and Datasets
• Face Detection with Feature Pyramids and Landmarks
• Wildest Faces: Face Detection and Recognition in Violent Settings
• Robust Face Detection via Learning Small Faces on Hard Images
• Improving Face Detection Performance with 3D-Rendered Synthetic Data
• KPNet: Towards Minimal Face Detector