目标检测--RON: Reverse Connection with Objectness Prior Networks for Object Detection
来源:互联网 发布:js tab选项卡 编辑:程序博客网 时间:2024/05/19 16:21
RON: Reverse Connection with Objectness Prior Networks for Object Detection
CVPR2017
https://github.com/taokong/RON
本文可以看作是对 SSD 的改进, SSD 对不同尺度特征图进行独立的检测,这里我们 reverse connection block 将相邻的特征图联系起来。同时使用 objectness prior 来有效降低目标的搜索空间。
3 Network Architecture
我们使用 VGG16 作为基础模型, VGG16有13个卷积层,3个全连接层,这里我们将 第 14,15 全连接层变为卷积层,使用一个2×2卷积核 步长为2 来降采样 FC7 的尺寸。用于检测的特征图尺寸分布为输入图像尺寸的 1/8 (conv 4 3), 1/16 (conv 5 3), 1/32 (conv 6) and 1/64 (conv 7)
RON object detection overview
3.1. Reverse Connection
怎么把相邻的特征图联系起来了?我们提出了一个 reverse connection block 来解决这个问题。 相邻的特征图尺寸差异通过 deconv 反卷积来消除
3.2. Reference Boxes
这里我们对每个尺度的特征图使用 2 scales and 5 aspect ratios 的 default boxes,
aspect ratios { 1/3,1/2, 1, 2,3}
3.3. Objectness Prior
针对 正负样本比例严重失调, the ratio between object and non-object samples is seriously imbalanced,这里我们使用 Objectness Prior 来过滤大部分负样本
3.4. Detection and Bounding Box Regression
A=10个 Reference Boxes
inception block 我们使用了一个比较简单的结构
3.5. Combining Objectness Prior with Detection
经过 objectness prior 过滤,只有很少一部分样本进行 back-propagation
4 Training and Testing
4.1. Loss Function
损失函数包括三个子损失函数: objectness prior,矩形框坐标,物体类别
其中α =β =1/3
4.2. Joint Training and Testing
Data augmentation :flipped,Randomly sampling a patch
Detection results on PASCAL VOC 2007 test set
Results on PASCAL VOC 2012 test set
MS COCO test-dev2015 detection results
6.1. Do Multiple Layers Help?
low resolution 384×384 input size,With 1.5G GPU memory at test phase, the speed of the network is 15 FPS, 3× faster than the Faster R-CNN counterpart
- 目标检测--RON: Reverse Connection with Objectness Prior Networks for Object Detection
- 【1707.01691】RON:Reverse Connection with Objectness Prior Networks for Object Detection
- 论文阅读-《RON-Reverse Connection with Objectness Prior Networks for Object Detection》
- 【论文笔记摘要】RON:Reverse connection with Objectness prior Networks
- 目标检测--Feature Pyramid Networks for Object Detection
- 目标检测“Feature Pyramid Networks for Object Detection”
- 目标检测“Perceptual Generative Adversarial Networks for Small Object Detection”
- 目标检测“Perceptual Generative Adversarial Networks for Small Object Detection”
- 目标检测“Perceptual Generative Adversarial Networks for Small Object Detection”
- 视频目标检测 - Object Detection from Video Tubelets with Convolutional Neural Networks
- 目标检测--PVANET: Deep but Lightweight Neural Networks for Real-time Object Detection
- 目标检测--PVANET: Deep but Lightweight Neural Networks for Real-time Object Detection
- 目标检测--Wide-Residual-Inception Networks for Real-time Object Detection
- 目标检测 Feature Pyramid Networks for Object Detection(FPN)论文笔记
- 特征金字塔特征用于目标检测:Feature Pyramid Networks for Object Detection
- 目标检测--Improving Object Detection With One Line of Code
- 目标检测:Improving Object Detection With One Line of Code
- Convolutional Patch Networks with Spatial Prior for Road Detection and Urban Scene Understanding
- 换行符
- 数据结构课程主页-2016级
- Increase and Decrease
- C++ 异常处理 catch(...)介绍
- HDU 6139 Galaxy at War(坑题+阶梯博弈)
- 目标检测--RON: Reverse Connection with Objectness Prior Networks for Object Detection
- 神经机器翻译中的领域自适应问题 Domain adaptation for NMT
- webmagic爬取职位信息,新手上路
- 为CheckBox设置点击样式(button属性)
- 小结
- python:单引号,双引号和三引号的区别
- hanlp中文处理包-文档
- Mac Android Studio 使用离线文档
- java生产者消费者模型