SFace: An Efficient Network for Face Detection in Large Scale Variations
arXiv:1804.06559
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.
References in corpus (8)
- Decoupled Weight Decay Regularization
- DSSD : Deconvolutional Single Shot Detector
- Focal Loss for Dense Object Detection
- DenseBox: Unifying Landmark Localization with End to End Object Detection
- Some Improvements on Deep Convolutional Neural Network Based Image Classification
- Face Detection through Scale-Friendly Deep Convolutional Networks
- From Facial Parts Responses to Face Detection: A Deep Learning Approach
- Scale-Aware Face Detection
Cited by in corpus (6)
- Detect Faces Efficiently: A Survey and Evaluations
- PyramidBox++: High Performance Detector for Finding Tiny Face
- WIDER Face and Pedestrian Challenge 2018: Methods and Results
- DuBox: No-Prior Box Objection Detection via Residual Dual Scale Detectors
- EMface: Detecting Hard Faces by Exploring Receptive Field Pyraminds
- Improving Face Detection Performance with 3D-Rendered Synthetic Data