Face Detection with the Faster R-CNN

TL;DR

This paper applies the Faster R-CNN model to face detection, achieving state-of-the-art results on major benchmarks by training on the large-scale WIDER face dataset.

Contribution

It demonstrates the effectiveness of Faster R-CNN for face detection and reports new state-of-the-art performance on FDDB and IJB-A benchmarks.

Findings

Achieved top performance on FDDB and IJB-A datasets.

Validated the effectiveness of Faster R-CNN for face detection.

Showed the benefit of training on large-scale datasets.

Abstract

The Faster R-CNN has recently demonstrated impressive results on various object detection benchmarks. By training a Faster R-CNN model on the large scale WIDER face dataset, we report state-of-the-art results on two widely used face detection benchmarks, FDDB and the recently released IJB-A.