READING NOTE: R-FCN: Object Detection via Region-based Fully Convolutional Networks
转载自:
http://blog.csdn.net/joshua_1988/article/details/51484412
TITLE: R-FCN: Object Detection via Region-based Fully Convolutional Networks
AUTHER: Jifeng Dai, Yi Li, Kaiming He, Jian Sun
ASSOCIATION: MSRA, Tsinghua University
FROM: arXiv:1605.06409
CONTRIBUTIONS
- A framework called Region-based Fully Convolutional Network (R-FCN) is develpped for object detection, which consists of shared, fully convolutional architectures.
- A set of position-sensitive score maps are introduced to enalbe FCN representing translation variance.
- A unique ROI pooling method is proposed to shepherd information from metioned score maps.
METHOD
- The image is processed by a FCN manner network.
- At the end of FCN, a RPN (Region Proposal Network) is used to generate ROIs.
- On the other hand, a score map of k 2 (C+1) channels is generated using a bank of specialized convolutional layers.
- For each ROI, a selective ROI pooling is utilized to generate a C+1 channel score map.
- The scores in the score map are averaged to vote for category.
- Another 4k 2 dim convolutional layer is learned for bounding box regression.
Training Details
- R-FCN is trained end-to-end with pre-computed region proposals. Both category and position are learnt with the loss function: L(s,t x,y,w,h )=L cls (s c ∗ )+λ[c ∗ >0]L reg (t,t ∗ ) .
- For each image, N proposals are generated and B out of N proposals are selected to train weights according to the highest losses. B is set to 128 in this work.
- 4-step alternating training is utilized to realizing feature sharing between R-FCN and RPN.
ADVANTAGES
- It is fast (170ms/image, 2.5-20x faster than Faster R-CNN).
- End-to-end training is easier to process.
- All learnable layers are convolutional and shared on the entire image, yet encode spatial information required for object detection.
DISADVANTAGES
- Compared with Single Shot methods, more computation resource is needed
READING NOTE: R-FCN: Object Detection via Region-based Fully Convolutional Networks相关推荐
- FCN的学习及理解(Fully Convolutional Networks for Semantic Segmentation)
大多数人接触"语义"都是在和文字相关的领域,或语音识别,期望机器能够识别你发出去的消息或简短的语音,然后给予你适当的反馈和回复.嗯,看到这里你应该已经猜到了,图像领域也是存在&qu ...
- 彻底讲透FCN语义分割开山之作Fully Convolutional Networks
FCN论文标题:Fully Convolutional Networks for Semantic Segmentation 论文下载地址:https://arxiv.org/abs/1411.40 ...
- 全卷积(FCN)论文阅读笔记:Fully Convolutional Networks for Semantic Segmentation
论文阅读笔记:Fully Convolutional Networks forSemantic Segmentation 这是CVPR 2015拿到best paper候选的论文. 论文下载地址:Fu ...
- (FCN)-Fully Convolutional Networks for Semantic Segmentation
文章目录 Fully Convolutional Networks for Semantic Segmentation 摘要 全局信息和局部信息 感受野 FCN算法架构 训练技巧 详细参考 Fully ...
- 【FCN】Fully Convolutional Networks for Semantic Segmentation学习
论文翻译 又是一个看不懂原文,又看不懂翻译的论文. semantic segmentation 图像语义分割 就是预测每个像素所属的对象类别 语义分割是指像素级地识别图像,即标注出图像中每个像素所属的 ...
- 深度学习论文阅读目标检测篇(三):Faster R-CNN《 Towards Real-Time Object Detection with Region Proposal Networks》
深度学习论文阅读目标检测篇(三):Faster R-CNN< Towards Real-Time Object Detection with Region Proposal Networks&g ...
- 目标检测经典论文——Faster R-CNN论文翻译:Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Net
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks Faster R-CNN:通过Region ...
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks(更快的RCNN:通过区域提议网络实现实时)
原文出处 感谢作者~ Faster R-CNN: Towards Real-Time Object Detection with Region ProposalNetworks Shaoqing Re ...
- 读书笔记:Faster R-CNN:Towards Real-Time Object Detection with Region Proposal Networks
Faster R-CNN:Towards Real-Time Object Detection with Region Proposal Networks 著名的faster R-CNN 当然应该好好 ...
最新文章
- Eclipse中git检出、更新、提交、合并分支、以及解决冲突
- 我的家乡-客家小山村
- 8.8-9 fsck、dd
- 2019年第十届蓝桥杯 - 省赛 - C/C++大学C组 - F. 旋转
- 新装ubuntu10.04后的一些设置
- echarts折线图相关
- string类的构造函数,拷贝构造函数,析构函数和赋值函数
- js模板引擎 之handlebars.js
- 扫描40亿可路由的 IPv4 地址后发现这些打印机的 IPP 端口遭暴露
- Android:获取最近打开app列表
- 终端天线—7.UWB天线仿真
- 怎样做小游戏挖金子(VC,源码5)
- 第三章:使用HiTool下载程序
- GitHub创建仓库导入项目
- foobar2000在线标签服务器,在Foobar2000播放器中从音乐名获取标签的技巧
- python大游戏_Python开发【项目】:大型模拟战争游戏(外星人入侵)
- win10上不了网服务器未响应,win10的DNS 服务器未响应
- 【历史上的今天】9 月 29 日:“美国支付宝” Stripe 正式上线;HotJava 面世;VR/AR 领域先驱诞生
- Location定位程序驱动合集
- 深度学习之 imgaug (图像增强)学习笔记