Precise Box Score: Extract More Information from Datasets to Improve the Performance of Face Detection

Abstract

For the training of face detection network based on R-CNN framework, anchors are assigned to be positive samples if intersection-over-unions (IoUs) with ground-truth are higher than the first threshold(such as 0.7); and to be negative samples if their IoUs are lower than the second threshold(such as 0.3). And the face detection model is trained by the above labels. However, anchors with IoU between first threshold and second threshold are not used. We propose a novel training strategy, Precise Box Score(PBS), to train object detection models. The proposed training strategy uses the anchors with IoUs between the first and second threshold, which can consistently improve the performance of face detection. Our proposed training strategy extracts more information from datasets, making better utilization of existing datasets. What's more, we also introduce a simple but effective model compression method(SEMCM), which can boost the performance of face detectors further. Experimental results show that the performance of face detection network can consistently be improved based on our proposed scheme.

References in corpus (11)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Distilling the Knowledge in a Neural Network
• R-FCN: Object Detection via Region-based Fully Convolutional Networks
• HyperNet: Towards Accurate Region Proposal Generation and Joint Object Detection
• From Facial Parts Responses to Face Detection: A Deep Learning Approach
• Detecting Faces Using Region-based Fully Convolutional Networks
• WIDER FACE: A Face Detection Benchmark
• Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neural Networks
• Face Detection with the Faster R-CNN
• Grid Loss: Detecting Occluded Faces
• Face R-CNN