Abstract
In recent year, tremendous strides have been made in face detection thanks to deep learning. However, most published face detectors deteriorate dramatically as the faces become smaller. In this paper, we present the Small Faces Attention (SFA) face detector to better detect faces with small scale. First, we propose a new scale-invariant face detection architecture which pays more attention to small faces, including 4-branch detection architecture and small faces sensitive anchor design. Second, feature maps fusion strategy is applied in SFA by partially combining high-level features into low-level features to further improve the ability of finding hard faces. Third, we use multi-scale training and testing strategy to enhance face detection performance in practice. Comprehensive experiments show that SFA significantly improves face detection performance, especially on small faces. Our real-time SFA face detector can run at 5 FPS on a single GPU as well as maintain high performance. Besides, our final SFA face detector achieves state-of-the-art detection performance on challenging face detection benchmarks, including WIDER FACE and FDDB datasets, with competitive runtime speed. Both our code and models will be available to the research community.
Highlights
Face detection is a fundamental step of many face related applications, such as face alignment [1], [2], face recognition [3], [4], face verification [5], [6] and face expression analysis
We propose the Small Faces Attention (SFA) face detector to seek out more faces with small scale
Unlike S3FD which merges different scale feature maps and forms a comprehensive face features, our work indicates that multi-branch detection modules in scale can be optimally learned separately
Summary
Face detection is a fundamental step of many face related applications, such as face alignment [1], [2], face recognition [3], [4], face verification [5], [6] and face expression analysis. Excellent face detectors can exactly classify and locate faces from an image. Deep learning methods especially convolutional neural networks (CNN) have achieved remarkable successes in a variety of computer vision tasks, ranging from image classification [7], [8] to object detection [9]–[12], which inspire face detection. Unlike traditional methods of hand-crafted features, CNN-based method can extract face features automatically. Anchor-based face detectors play a dominant role in CNN-based face detectors. They detect faces by classifying and regressing a series of pre-set anchors, which are generated by regularly tiling a collection of boxes with different scale on the images
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
