[深度学习论文笔记][Object Detection] Faster R-CNN: Towards Real-Time Object

Faster R-CNN通过在conv5层后插入区域提议网络(RPN)来解决目标检测速度问题,无需外部区域提议。RPN后使用RoI池化和上游分类器及边界框回归器,类似于Fast R-CNN。网络同时预测多个尺度和宽高比的区域提议,并使用4种损失进行联合训练:RPN分类、RPN回归、Fast R-CNN分类和Fast R-CNN回归。
摘要由CSDN通过智能技术生成
Ren, Shaoqing, et al. “Faster R-CNN: Towards real-time object detection with region proposal networks.” Advances in neural information processing systems. 2015. (Citations:
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.



2 Region Proposal Network

Slide a small window (3 × 3 in our case) on the conv5 feature map. For each window, we

  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值