------------------------------------------------------------------------
About Face detection
------------------------------------------------------------------------
1、Finding Tiny Faces
Code:https://github.com/peiyunh/tiny
小目标检测难3大原因:目标本身尺度变化、图像分辨率以及环境因素。本文针对多尺度训练了不同的检测器,这些检测器所用特征来自同一网络的不同层级。此外,还充分利用了目标周边信息。
2、Seeing Small Faces from Robust Anchor’s Perspective
基于anchor设计原理解决小脸检测不到的问题。
3、Face-MagNet: Magnifying Feature Maps to Detect Small Faces
Code:https://github.com/po0ya/face-magnet
基于Faster-RCNN框架提出Face-MagNet网络(在人脸建议和分类前放大特征图的判别能力)而无需任何跳过或残差连接。在RPN中和ROI前都加了一组反卷积层。另外,评估了其他3种针对尺度问题而有较好调整架构的方法:context pooling, skip connections, and scale partitioning.
4、Detecting and counting tiny faces
Code:https://github.com/alexattia/ExtendedTinyFaces
对Finding Tiny Faces这篇文章的深入理解,类似的方法。
5、SSH: Single Stage Headless Face Detector
Code:https://github.com/mahyarnajibi/SSH
单阶段检测器,速度快,占用内存少,在不同深度的网络层进行人脸检测,用于检测大、中、小人脸。
6、S3FD: Single Shot Scale-invariant Face Detector
Code:https://github.com/sfzhang15/SFD
(1) proposing a scale-equitable face detection framework to handle different scales of faces well.
(2) improving the recall rate of small faces by a scale compensation anchor matching strategy.
(3) reducing the false positive rate of small faces via a max-out background label.
7、Multi-Path Region-Based Convolutional Neural Network for Accurate Detection of Unconstrained “Hard Faces”
a two-stage cascaded face detection framework:
(1) a Multi-Path Region Proposal Network(MP-RPN),利用3个平行特征图的输出预测不同尺度的候选人脸区域,嵌有带有上采样过滤的卷积层和新提出的产生“难”例采样层。
(2) a Boosted Forests classifier,利用候选人脸区域内的深