READING NOTE: Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neura
来源:互联网 发布:win7卸载ubuntu双系统 编辑:程序博客网 时间:2024/06/05 16:16
TITLE: Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neural Networks
AUTHER: Sean Bell, C. Lawrence Zitnick, Kavita Bala, Ross Girshick Yan
ASSOCIATION: Cornell University, Microsoft Research
FROM: arXiv:1512.04143
CONTRIBUTIONS
- ION architecture is introduce that leverages context and multi-scale skip pooling for object detection. Use the information both inside and outside the ROI to determine the detection result.
METHOD
The main steps of the method is shown in the following figure.
- The image is first fed into a CNN, e.g.VGG16.
- ROI proposals are generated in the same way of Fast R-CNN.
- The information within the ROI are extracted by ROI pooling on different feature maps from different convolutional layers of different scales.
- The information outside the ROI are extracted by 2 successive 4-direction IRNNs. And ROI pooling is used to extract features.
- The pooled features are L2 nomalized and concated. Then a 1X1 conv layer is used to reduce the dimension.
- Two branches are learned to predict category and location.
some details
A 4-direction IRNN contains 4 independent IRNNs and each IRNN moves in different directions (left, right, up and down). The internal IRNN computations are splitted into separate logical layers. the input-to-hidden transition is implemented by a 1x1 convolution, and its computation can be shared across different directions.
ADVANTAGES
- The proposed detector works better on smaller objects compared with other works.
- Both local and global information are take into account.
- Skip pooling uses the informaiton of different scales.
- Two successive 4-direction IRNN cover the information form the whole image.
0 0
- READING NOTE: Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neura
- 论文笔记 | Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neural Netwo
- 论文《Inside-Outside Net: Detecting Objects in Context with skip pooling and Recurrent Neural Networks》
- READING NOTE: Learning to Segment Moving Objects in Videos
- READING NOTE: Pooling the Convolutional Layers in Deep ConvNets for Action Recognition
- Inbound, outbound, inside and outside
- Reading and writing Serializable objects
- What is "inside dialog" and "outside dialog"
- Detecting Designmode in ASP.Net
- Timer Objects in Windows Services with C#.NET
- #Paper Reading# Abstractive Sentence Summarization with Attentive Recurrent Neural Networks
- note_1 about detecting with haar and adboost
- Dynamic Entity Representation with Max-pooling Improves Machine Reading
- Detecting a mobile browser in ASP.NET
- Detecting a mobile browser in ASP.NET
- Context-aware Natural Language Generation with Recurrent Neural Networks
- Android: Reading, using and working with XML data and web services in Android
- 用 Python 和 OpenCV 检测图片上的条形码Detecting Barcodes in Images with Python and OpenCV
- HTTP头Content-Type
- 关于mtk GPIO口的定制
- Centos7下配置Redis开机自启动
- 研究微型真空水泵有背压工况下的寿命
- 输入流转为字符串
- READING NOTE: Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neura
- 第十一周项目训练9 存储班长信息的学生类
- 数据库的拆分
- 微型真空水泵WAJ280降低工作电压测试报告
- JZOJ.3400【GDOI2014模拟】旅行 解题报告
- 微型气泵最大启动压力试验报告
- 2016-06-01错误日志-部署
- js函数(类)的继承机制的设计与实现(四)
- 【HTML5/CSS/JS】A list of Font Awesome icons and their CSS content values(一)