Log In Sign Up

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

by   Jianfeng Wang, et al.

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 which outperforms the state-of-art algorithms by almost one order of magnitude in speed while achieves comparative performance.


page 2

page 9

page 14


Anchor Cascade for Efficient Face Detection

Face detection is essential to facial analysis tasks such as facial reen...

Face Attention Network: An Effective Face Detector for the Occluded Faces

The performance of face detection has been largely improved with the dev...

Face Detection with the Faster R-CNN

The Faster R-CNN has recently demonstrated impressive results on various...

Seeing Small Faces from Robust Anchor's Perspective

This paper introduces a novel anchor design to support anchor-based face...

Towards Flops-constrained Face Recognition

Large scale face recognition is challenging especially when the computat...

One-shot Face Recognition by Promoting Underrepresented Classes

We study in this paper the problem of one-shot face recognition, with th...

Two-Stream Neural Networks for Tampered Face Detection

We propose a two-stream network for face tampering detection. We train G...