Faster RCNN

最新推荐文章于 2020-10-06 15:42:32 发布

*Major*

最新推荐文章于 2020-10-06 15:42:32 发布

阅读量271

点赞数

本文链接：https://blog.csdn.net/qq_41375318/article/details/103155285

版权

Faster RCNN

-Model(pytorch版本

视频教程：B站
代码地址：Gitee、Github
存储地址：
百度云 -提取码：6cgu
Google云

1.一论文导读
2.二论文精读
3.三代码实现
4.四问题思索

《Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks》
—two stage的检测网络的经典代表
作者：Shaoqing Ren, Kaiming He, Ross Girshick, Jian Sun
单位：
发表会议及时间：2015.4

Submission history
From: Kaiming He [view email]
[v1] Thu, 4 Jun 2015 07:58:34 UTC (2,095 KB)
[v2] Sun, 13 Sep 2015 07:54:00 UTC (2,095 KB)
[v3] Wed, 6 Jan 2016 06:30:17 UTC (6,102 KB)

https://arxiv.org/abs/1506.01497

Abstract

State-of-the-art object detection networks depend on region proposal algorithms to hypothesize object locations. Advances like SPPnet and Fast R-CNN have reduced the running time of these detection networks, exposing region proposal computation as a bottleneck.

In this work, we introduce a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals. An RPN is a fully convolutional network that simultaneously predicts object bounds and objectness scores at each position.

The RPN is trained end-to-end to generate high-quality region proposals, which are used by Fast R-CNN for detection. We further merge RPN and Fast R-CNN into a single network by sharing their convolutional features—using the recently popular terminology of neural networks with ‘attention’ mechanisms, the RPN component tells the unified network where to look.

For the very deep VGG-16 model, our detection system has a frame rate of 5fps (including all steps) on a GPU, while achieving state-of-the-art object detection accuracy on PASCAL VOC 2007, 2012, and MS COCO datasets with only 300 proposals per image. In ILSVRC and COCO 2015 competitions, Faster R-CNN and RPN are the foundations of the 1st-place winning entries in several tracks. Code has been made publicly available.