RCNN, Fast-RCNN, Faster-RCNN

http://closure11.com/rcnn-fast-rcnn-faster-rcnn%E7%9A%84%E4%B8%80%E4%BA%9B%E4%BA%8B/

Faster-RCNN 论文笔记

Faster RCNN由两个模块组成：
1.deep fully convolutional network that proposes regions
2.Fast R-CNN detector that uses the proposed regions

RPN：tells the Fast R-CNN module where to look.

Region Proposal Networks
input: an image (of any size)
output: a set of rectangular object proposals,each with an objectness score
We model this process with a fully convolutional network.

Because our ultimate goal is to share computation with a Fast R-CNN object detection network,we assume that both nets share a common set of convolutional layers.
In our experiments, we investigate the Zeiler and Fergus model [32] (ZF), which has 5 shareable convolutional layers and the Simonyan and Zisserman model [3] (VGG-16), which has 13 shareable convolutional layers.

To generate region proposals,we slide a small network over the convolutional feature map output by the last shared convolutional layer. This small network takes as input an n × n spatial window of the input convolutional feature map.