人脸检测--Faceness-Net: Face Detection through Deep Facial Part Responses
来源:互联网 发布:红色网络家园安装包 编辑:程序博客网 时间:2024/06/14 08:35
Faceness-Net: Face Detection through Deep Facial Part Responses PAMI2017
From Facial Parts Responses to Face Detection: A Deep Learning Approach ICCV2015
http://shuoyang1213.me/projects/Faceness/Faceness.html
https://pan.baidu.com/s/1qWFwqFM Password: 4q8y
本文针对人脸检测问题,从 facial attributes 的角度来解决人脸检测中的 severe occlusions 和 large pose variation
在人脸检测中使用 facial attributes supervision 的好处:
1)Discovering facial parts responses supervised by facial attributes 人脸具有唯一的结构
2) Computing faceness score from responses configurations 由人脸的局部到整体的推导
3) Refining the face hypotheses 人脸候选区域的进一步验证
本文和我们以前的工作【24,25】相比较,主要的改进在于设计了一个更有效的CNN,提高了速度和精度,具体改进有:
1)以前我们是用独立的网络来学习各个 facial parts,现在 我们共享了这些部件特征, share feature representations between these attribute-aware networks,这么做降低网络的参数量(( ∼ 83% fewer parameters),同时提升了网络的鲁棒性
2)候选区域提取模块嵌入到整个网络中,而不是独立的模块 This design not only leads to improved computation efficiency but also higher recall rate
3)更多的分析和实验
3 Faceness-Net
算法的整个流程是首先进行人脸局部特征的检测,然后从局部到整体得到人脸候选区域,再对人脸候选区域进行人脸识别和矩形框坐标回归
First stage
每个人脸局部特征我们使用一个CNN来检测 attribute-aware networks,一共五个特征属性: hair, eyes, nose, mouth, and beard
有了局部特征属性的响应,有局部推理出人脸候选区域
Second stage
训练一个多任务的CNN来完成人脸二分类和矩形框坐标回归 face classification and bounding box regression are jointly optimized
3.1 Attribute-Aware Networks
Network structure 网络结构
Shared representation 特征共享 网络的前半部分网络参数基本一样,所以可以实现共享, 降低网络参数量 83%
3.2 Learning to Generate Partness Maps
人脸局部属性归类
3.3 Generating Candidate Windows
一般来说有两种方法可以用于候选区域生成:Generic object proposal 和 Template proposal(RPN)。但是这两种方法都是针对 generic objects 设计的,not suitable to propose windows specific to faces。我们提出了一个针对人脸的好方法 3.4
3.4 Ranking Windows by Faceness Score
3.5 Face Detection
These face proposals can be subsequently fed to the multi-task CNN
fine-tune the first branch of the multi-task CNN for face classification and the second branch for bounding box regresssion
The runtime of the proposed Faceness-Net-SR-TP is 40 ms on a single Nvidia Titan X GPU. The time includes 10 ms to generate faceness proposals with the height of testing image no more than 300 pixels.
- 人脸检测--Faceness-Net: Face Detection through Deep Facial Part Responses
- From Facial Parts Responses to Face Detection: A Deep Learning Approach
- 论文《From Facial Parts Responses to Face Detection: A Deep Learning Approach》笔记
- From Facial Parts Responses to Face Detection: A Deep Learning Approach
- 【论文笔记】From Facial Parts Responses to Face Detection: A Deep Learning Approach
- 多尺度人脸检测--Face Detection through Scale-Friendly Deep Convolutional Networks
- 【论文笔记】From Facial Parts Responses to Face Detection(ICCV 2015)
- Facial Landmark Detection(人脸特征点检测)
- Facial Landmark Detection(人脸特征点检测)
- Facial Landmark Detection(人脸特征点检测)
- 人脸特征点检测(Facial landmark detection)
- Facial Landmark Detection(人脸特征点检测)
- OpenCV - 人脸检测(face detection) 代码
- Opencv face detection人脸检测
- 人脸检测--Scale-Aware Face Detection
- Improving Multiview Face Detection with Multi-Task Deep Convolutional Neural Networks 基于深度学习的人脸检测算法
- 人脸关键点: DCNN-Deep Convolutional Network Cascade for Facial Point Detection
- 人脸关键点:TCDCN-Facial Landmark Detection by Deep Multi-task Learning
- C6748EDMA_GPIO_中断学习笔记
- CentOS7关闭防火墙和SELinux
- swift 获取app、ios 版本号及设备信息
- PHP的RSA签名
- java-第三天
- 人脸检测--Faceness-Net: Face Detection through Deep Facial Part Responses
- QT实现CSDN上传资源管理助手Demo之(1)抓包分析HTTP协议
- C语言中的static
- 小卫星背后的大生意,中国创业者们的“太空竞赛”
- 钛媒体创始人赵何娟:公司大多死于习惯,而不是死于欲望
- 京东正式进军房地产;11月起购买火车票可用微信支付;乐视网被曝多名高管离职丨价值早报
- 冒泡排序
- git查看文件修改记录
- iOS 11开发教程(五)iOS11模拟器介绍二