SFace: An Efficient Network for Face Detection in Large Scale Variations
arXiv (Cornell University)Published 18 April 2018Open access
Jianfeng Wang, Ye Yuan, Boxun Li, Gang Yu, Jian Sun
Citations20
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
A novel algorithm called SFace is presented, which efficiently integrates the anchor-based method and anchor-free method to address the scale issues of face detection and shows promising results on the new 4K-Face benchmarks.
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.
Keywords
Computer Science
Deep Residual Learning for Image Recognition
222,082 Citations2016Kaiming He, Xiangyu Zhang +2 more
This work presents a residual learning framework to ease the training of networks that are substantially deeper than those used previously, and provides comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth.
International Journal of Computer VisionImageNet Large Scale Visual Recognition Challenge
40,207 Citations2015Olga Russakovsky, Jia Deng +10 more
The creation of this benchmark dataset and the advances in object recognition that have been possible as a result are described, and the state-of-the-art computer vision accuracy with human accuracy is compared.
Feature Pyramid Networks for Object Detection
28,681 Citations2017Tsung-Yi Lin, Piotr Dollár +4 more
This paper exploits the inherent multi-scale, pyramidal hierarchy of deep convolutional networks to construct feature pyramids with marginal extra cost and achieves state-of-the-art single-model results on the COCO detection benchmark without bells and whistles.
Xception: Deep Learning with Depthwise Separable Convolutions
18,952 Citations2017François Chollet
This work proposes a novel deep convolutional neural network architecture inspired by Inception, where Inception modules have been replaced with depthwise separable convolutions, and shows that this architecture, dubbed Xception, slightly outperforms Inception V3 on the ImageNet dataset, and significantly outperforms it on a larger image classification dataset.
Rapid object detection using a boosted cascade of simple features
18,097 Citations2005Paul Viola, Michael Jones
A machine learning approach for visual object detection which is capable of processing images extremely rapidly and achieving high detection rates and the introduction of a new image representation called the "integral image" which allows the features used by the detector to be computed very quickly.
Deep Face Recognition
5,074 Citations2015Omkar Parkhi, Andrea Vedaldi +1 more
It is shown how a very large scale dataset can be assembled by a combination of automation and human in the loop, and the trade off between data purity and time is discussed.
A discriminatively trained, multiscale, deformable part model
2,882 Citations2008Pedro F. Felzenszwalb, David McAllester +1 more
A discriminatively trained, multiscale, deformable part model for object detection, which achieves a two-fold improvement in average precision over the best performance in the 2006 PASCAL person detection challenge and outperforms the best results in the 2007 challenge in ten out of twenty categories.
Supervised Descent Method and Its Applications to Face Alignment
1,947 Citations2013Xuehan Xiong, Fernando De la Torre
A Supervised Descent Method (SDM) is proposed for minimizing a Non-linear Least Squares (NLS) function and achieves state-of-the-art performance in the problem of facial feature detection.
WIDER FACE: A Face Detection Benchmark
1,802 Citations2016Shuo Yang, Ping Luo +2 more
There is a gap between current face detection performance and the real world requirements, and the WIDER FACE dataset, which is 10 times larger than existing datasets is introduced, which contains rich annotations, including occlusions, poses, event categories, and face bounding boxes.
arXiv (Cornell University)DSSD : Deconvolutional Single Shot Detector
1,634 Citations2017Cheng-Yang Fu, Wei Liu +3 more
This paper combines a state-of-the-art classifier with a fast detection framework and augments SSD+Residual-101 with deconvolution layers to introduce additional large-scale context in object detection and improve accuracy, especially for small objects.
Fast Human Detection Using a Cascade of Histograms of Oriented Gradients
1,398 Citations2006Qiang Zhu, Mei-Chen Yeh +2 more
This work integrates the cascade-of-rejectors approach with the Histograms of Oriented Gradients (HoG) features to achieve a fast and accurate human detection system that can process up to 30 frames per second while maintaining an accuracy level similar to existing methods.
arXiv (Cornell University)Focal Loss for Dense Object Detection
1,350 Citations2017Tsung-Yi Lin, Priya Goyal +3 more
Face Alignment Across Large Poses: A 3D Solution
1,164 Citations2016Xiangyu Zhu, Zhen Lei +3 more
Finding Tiny Faces
742 Citations2017Peiyun Hu, Deva Ramanan
The role of scale in pre-trained deep networks is explored, providing ways to extrapolate networks tuned for limited scales to rather extreme ranges and demonstrating state-of-the-art results on massively-benchmarked face datasets.
High-fidelity Pose and Expression Normalization for face recognition in the wild
583 Citations2015Xiangyu Zhu, Zhen Lei +3 more
A High-fidelity Pose and Expression Normalization (HPEN) method with 3D Morphable Model (3DMM) which can automatically generate a natural face image in frontal pose and neutral expression and an inpainting method based on Possion Editing to fill the invisible region caused by self occlusion is proposed.
arXiv (Cornell University)Decoupled Weight Decay Regularization
494 Citations2017Ilya Loshchilov, Frank Hutter
arXiv (Cornell University)DenseBox: Unifying Landmark Localization with End to End Object Detection
454 Citations2015Lichao Huang, Yi Yang +2 more
DenseBox is introduced, a unified end-to-end FCN framework that directly predicts bounding boxes and object class confidences through all locations and scales of an image and shows that when incorporating with landmark localization during multi-task learning, DenseBox further improves object detection accuray.
Aggregate channel features for multi-view face detection
301 Citations2014Bin Yang, Junjie Yan +2 more
Following the learning pipelines in Viola-Jones framework, the multi-view face detector using aggregate channel features shows competitive performance against state-of-the-art algorithms on AFW and FDDB test-sets, while runs at 42 FPS on VGA images.
arXiv (Cornell University)Some Improvements on Deep Convolutional Neural Network Based Image Classification
206 Citations2013Andrew Howard
International Journal of Computer VisionOn the Design of Cascades of Boosted Ensembles for Face Detection
167 Citations2007S. Charles Brubaker, Jianxin Wu +3 more
A novel method is proposed for making decisions about how many hypotheses to include in an ensemble and the appropriate balance of detection and false positive rates in the individual stages, which exploits the shape of the stage ROC curves in ways that have been previously ignored.
To boost or not to boost? On the limits of boosted trees for object detection
131 Citations2016Eshed Ohn-Bar, Mohan M. Trivedi
This study reveals the limited modeling capacity of the common boosted trees model, motivating a need for architectural changes in order to compete with multi-level and very deep architectures.
arXiv (Cornell University)Face Detection through Scale-Friendly Deep Convolutional Networks
115 Citations2017Shuo Yang, Yuanjun Xiong +2 more
It is shown that faces with different scales can be modeled through a specialized set of deep convolutional networks with different structures and these detectors can be seamlessly integrated into a single unified network that can be trained end-to-end.
arXiv (Cornell University)From Facial Parts Responses to Face Detection: A Deep Learning Approach
103 Citations2015Shuo Yang, Ping Luo +2 more
SSH: Single Stage Headless Face Detector
69 Citations2017Mahyar Najibi, Pouya Samangouei +2 more
The Single Stage Headless (SSH) face detector is introduced, which is able to achieve state-of-the-art results while removing the “head” of its underlying classification network – i.e. all fully connected layers in the VGG-16 which contains a large number of parameters.