SFace: An Efficient Network for Face Detection in Large Scale Variations

TL;DR

SFace is a novel face detection network that effectively handles large scale variations, achieving high speed and accuracy, and is validated on a new 4K-Face dataset and the WIDER FACE benchmark.

Contribution

The paper introduces SFace, a new efficient face detection algorithm that combines anchor-based and anchor-free methods to address scale variation challenges.

Findings

Achieves 80% AP at 50 fps on WIDER FACE

Outperforms state-of-the-art in speed by nearly tenfold

Shows promising results on the 4K-Face dataset

Abstract

Face detection serves as a fundamental research topic for many applications like face recognition. Impressive progress has been made especially with the recent development of convolutional neural networks. However, the issue of large scale variations, which widely exists in high resolution images/videos, has not been well addressed in the literature. In this paper, we present a novel algorithm called SFace, which efficiently integrates the anchor-based method and anchor-free method to address the scale issues. A new dataset called 4K-Face is also introduced to evaluate the performance of face detection with extreme large scale variations. The SFace architecture shows promising results on the new 4K-Face benchmarks. In addition, our method can run at 50 frames per second (fps) with an accuracy of 80% AP on the standard WIDER FACE dataset, which outperforms the state-of-art algorithms by almost one order of magnitude in speed while achieves comparative performance.