HAMBox: Delving Into Mining High-Quality Anchors on Face Detection

Yang Liu, Xu Tang, Junyu Han, Jingtuo Liu, Dinger Rui, Xiang Wu; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020, pp. 13046-13054

Abstract


Current face detectors utilize anchors to frame a multi-task learning problem which combines classification and bounding box regression. Effective anchor design and anchor matching strategy enable face detectors to localize faces under large pose and scale variations. However, we observe that, more than 80% correctly predicted bounding boxes are regressed from the unmatched anchors (the IoUs between anchors and target faces are lower than a threshold) in the inference phase. It indicates that these unmatched anchors perform excellent regression ability, but the existing methods neglect to learn from them. In this paper, we propose an Online High-quality Anchor Mining Strategy (HAMBox), which explicitly helps outer faces compensate with high-quality anchors. Our proposed HAMBox method could be a general strategy for anchor-based single-stage face detection. Experiments on various datasets, including WIDER FACE, FDDB, AFW and PASCAL Face, demonstrate the superiority of the proposed method.

Related Material


[pdf]
[bibtex]
@InProceedings{Liu_2020_CVPR,
author = {Liu, Yang and Tang, Xu and Han, Junyu and Liu, Jingtuo and Rui, Dinger and Wu, Xiang},
title = {HAMBox: Delving Into Mining High-Quality Anchors on Face Detection},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2020}
}