# HAMBox: Delving into Online High-quality Anchors Mining for Detecting Outer Faces

arXiv: https://arxiv.org/abs/1912.09231 · HTML: https://mlsanity.com/paper/1912.09231/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Dec 2019.

## Built on by (most cited first, 4 of 4)

- [Sample and Computation Redistribution for Efficient Face Detection](https://mlsanity.com/paper/2105.04714/) (2021)
- [YOLO5Face: Why Reinventing a Face Detector](https://mlsanity.com/paper/2105.12931/) (2021)
- [MogFace: Towards a Deeper Appreciation on Face Detection](https://mlsanity.com/paper/2103.11139/) (2021)
- [Variational Pedestrian Detection](https://mlsanity.com/paper/2104.12389/) (2021)

## Abstract (arXiv)

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. Furthermore, our team win the championship on the Face Detection test track of WIDER Face and Pedestrian Challenge 2019. We will release the codes with PaddlePaddle.