[深度学习论文笔记][Object Detection] Faster R-CNN: Towards Real-Time Object
来源:互联网 发布:三星手机智能网络切换 编辑:程序博客网 时间:2024/05/29 10:39
444).
1 Motivation
Region proposals are the test-time computational bottleneck in state-of-the-art detection systems.We solve this issue by inserting a Region Proposal Network (RPN) after the conv5 layer to produce region proposals directly. Thus, there is no need for external region proposals. After RPN, use RoI pooling and an upstream classifier and bounding box regressor just like Fast R-CNN. See Fig.
Slide a small window (3 × 3 in our case) on the conv5 feature map. For each window, we simultaneously predict multiple region proposals with a wide range of scales and aspect ratios, where the number of maximum possible proposals for each location is denoted as N.
proposal. The regression head has 4N outputs encoding the offsets to N reference boxes, which we call anchors. By default we use 3 scales and 3 aspect ratios, yielding N = 9 anchors at each sliding position. For a conv5 feature map of a size H × W, there are HWN anchors in total.
Anchors are translation invariant, both in terms of the anchors and the functions that compute proposals relative to the anchors. If one translates an object in an image, the
proposal should translate and the same function should be able to predict the proposal in either location.
3 Training Details
We assign a positive label to two kinds of anchors:
• The anchor with the highest IoU overlap with a ground-truth box.
• The anchor that has an IoU overlap higher than 0.7 with any ground-truth box.
We adopt the first condition for the reason that in some rare cases the second condition may find no positive sample. a
We assign a negative label to a non-positive anchor if its IoU ratio is lower than 0.3 for all ground-truth boxes. Anchors that are neither positive nor negative do not contribute to the training objective.
We joint training the whole network, it has four losses.
• RPN classification (anchor good/bad).
• RPN regression (anchor → proposal).
• Fast R-CNN classification (over classes).
• Fast R-CNN regression (proposal → box).
4 Result
See Tab.
- [深度学习论文笔记][Object Detection] Faster R-CNN: Towards Real-Time Object
- 论文笔记:Faster R-CNN:Towards Real-Time Object Detection with Region Proposal Networks
- 论文笔记:Faster R-CNN:Towards Real-Time Object Detection with Region Proposal Networks
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks论文笔记
- 论文笔记:Faster R-CNN:Towards Real-Time Object Detection with Region Proposal Networks
- 【论文笔记】Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- 论文笔记| Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks----论文笔记
- 论文笔记:Faster R-CNN:Towards Real-Time Object Detection with Region Proposal Networks
- 论文笔记:Faster R-CNN:Towards Real-Time Object Detection with Region Proposal Networks
- 论文笔记:Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks论文笔记
- RCNN学习笔记(3):《Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks》
- 【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
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- RCNN(四)Faster R-CNN:Towards Real-Time Object Detection with Region Proposal Networks
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- have you declared this activity in your AndroidManifest.xml?
- 1380 没有上司的舞会
- 解决办法:IntelliJ Java:-source 1.3中不支持,使用-source 5 或更高的版本一启用
- JavaScript 自定义函数:compose
- Android开发之获取手机短信验证码
- [深度学习论文笔记][Object Detection] Faster R-CNN: Towards Real-Time Object
- NSWOJ2180 - 最大的数
- redis 字典
- selected device is not a touchscreen I understand
- 创建一个Django后台帐号
- POJ 3723 conscription 最大生成树
- 小白也能当大神-mysql数据库引擎分析
- 11.9模拟赛
- Android-分析并优化首页启动时间