# FA-RPN: Floating Region Proposals for Face Detection

arXiv: https://arxiv.org/abs/1812.05586 · HTML: https://mlsanity.com/paper/1812.05586/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Dec 2018.

## Built on by (most cited first, 12 of 12)

- [Tracking Pedestrian Heads in Dense Crowd](https://mlsanity.com/paper/2103.13516/) (2021)
- [Going Deeper Into Face Detection: A Survey](https://mlsanity.com/paper/2103.14983/) (2021)
- [CRFace: Confidence Ranker for Model-Agnostic Face Detection Refinement](https://mlsanity.com/paper/2103.07017/) (2021)
- [Detect Faces Efficiently: A Survey and Evaluations](https://mlsanity.com/paper/2112.01787/) (2021)
- [EResFD: Rediscovery of the Effectiveness of Standard Convolution for Lightweight Face Detection](https://mlsanity.com/paper/2204.01209/) (2022)
- [Scale Normalized Image Pyramids with AutoFocus for Object Detection](https://mlsanity.com/paper/2102.05646/) (2021)
- [A Survey on Deep Domain Adaptation and Tiny Object Detection Challenges, Techniques and Datasets](https://mlsanity.com/paper/2107.07927/) (2021)
- [EfficientFace: An Efficient Deep Network with Feature Enhancement for Accurate Face Detection](https://mlsanity.com/paper/2302.11816/) (2023)
- [EfficientSRFace: An Efficient Network with Super-Resolution Enhancement for Accurate Face Detection](https://mlsanity.com/paper/2306.02277/) (2023)
- [Wide Aspect Ratio Matching for Robust Face Detection](https://mlsanity.com/paper/2103.05993/) (2021)
- [Bounding-box deep calibration for high performance face detection](https://mlsanity.com/paper/2110.03892/) (2021)
- [Semantic-Guided Natural Language and Visual Fusion for Cross-Modal Interaction Based on Tiny Object Detection](https://mlsanity.com/paper/2511.05474/) (2025)

## Abstract (arXiv)

We propose a novel approach for generating region proposals for performing face-detection. Instead of classifying anchor boxes using features from a pixel in the convolutional feature map, we adopt a pooling-based approach for generating region proposals. However, pooling hundreds of thousands of anchors which are evaluated for generating proposals becomes a computational bottleneck during inference. To this end, an efficient anchor placement strategy for reducing the number of anchor-boxes is proposed. We then show that proposals generated by our network (Floating Anchor Region Proposal Network, FA-RPN) are better than RPN for generating region proposals for face detection. We discuss several beneficial features of FA-RPN proposals like iterative refinement, placement of fractional anchors and changing anchors which can be enabled without making any changes to the trained model. Our face detector based on FA-RPN obtains 89.4% mAP with a ResNet-50 backbone on the WIDER dataset.