FA-RPN: Floating Region Proposals for Face Detection

Mahyar Najibi, Bharat Singh, Larry S. Davis; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 7723-7732

Abstract


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 (which can be enabled without re-training) like iterative refinement, placement of fractional anchors and changing size/shape of anchors. Our face detector based on FA-RPN obtains 89.4% mAP with a ResNet-50 backbone on the WIDER dataset.

Related Material


[pdf]
[bibtex]
@InProceedings{Najibi_2019_CVPR,
author = {Najibi, Mahyar and Singh, Bharat and Davis, Larry S.},
title = {FA-RPN: Floating Region Proposals for Face Detection},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2019}
}