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

TL;DR

This paper introduces Precise Box Score, a novel training strategy that leverages more dataset information by utilizing anchors with intermediate IoUs, significantly enhancing face detection performance.

Contribution

The paper proposes a new training method, Precise Box Score, that improves face detection by using previously ignored anchors and introduces an effective model compression technique.

Findings

Performance of face detection networks is consistently improved.

Utilizing intermediate IoU anchors enhances training effectiveness.

Model compression further boosts detection accuracy.

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.