专栏首页深度学习计算机视觉【ECCV 2018 .Jian Sun】DetNet: A Backbone network for Object Detection

【ECCV 2018 .Jian Sun】DetNet: A Backbone network for Object Detection

【Background】:ECCV is one of the top conferences in computer vision,In this blog,I will introduce an paper from Sun Jian team, which is about a backbone network for object detection.What is worth mentioning is that this paper does not have any formula.

paper name: DetNet: A Backbone network for Object Detection paper url: https://arxiv.org/abs/1804.06215

paper-information

1、【Abstract】

Object detection is a heavily researched topic in computer vision. It aims at finding “where” and “what” each object instance is when given an image.

In network structure, recent CNN based detectors are usually split into two parts. The one is backbone network,and the other is detection business part. you can see the picture below to understand this.

1.png

2、【Motivation】

the existing backbone networks usually have some problems,because they are desighed for classification task at first,there is no doubt that there are differences between different tasks(classification and detection).so,de signing a new backbone networks for detection is become very neccessary.

2.png

3、【The problems of exist backbone network】

2.png

4、【Comparisons of different backbones used in FPN】

3.png

5、【Contributions】

4.png

6、【DetNet design】

5.png

6.png

7、【More details】

the author adopt ResNet-50 as baseline, which is widely used as the backbone network in a lot of object detectors. To fairly compare with the ResNet-50, we keep stage 1,2,3,4 the same as original ResNet-50 for our DetNet.the more details you can see picture 7.png.

7.png

apply bottleneck with dilation as a basic network block to efficiently enlarge the receptive filed. Since dilated convolution is still time consuming,our stage 5 and stage 6 keep the same channels as stage 4 (256 input channels for bottleneck block). This is different from traditional backbone design,which will double channels in a later stage.

More information about dilation:https://blog.csdn.net/jzrita/article/details/72639969

8、【Experiment】

4.png

5.png

6.png

7.png

8.png

9.png

10.png

11.png

12.png

13.png

14.png

本文参与腾讯云自媒体分享计划,欢迎正在阅读的你也加入,一起分享。

我来说两句

0 条评论
登录 后参与评论

相关文章

  • 递归处理数字全排列算法

    问题背景### 递归很常用,但确实不好理解,下边这段程序是用来进行数字全排列的 由于很多算法需要讲数字全排列后再来暴力求解问题,所以学会数字的全排列还是很有意...

    张俊怡
  • 软件测试正交测试法 举个例子

    正交实验法的介绍 正交试验法是研究多因素、多水平的一种试验法,它是利用正交表来对试验进行设计,通过少数的试验替代全面试验 在一项试验中,把影响试验结果的量...

    张俊怡
  • 数据挖掘之认识数据学习笔记相关术语熟悉

    相关术语熟悉 首先认识数据的属性 属性是一个数据字段,表示数据对象的一个特征 标称属性 标称属性的值是一些符号或事物的名称,这一些值可以看做是枚举的 比如,职...

    张俊怡
  • Data Analysis

    林清猫耳
  • Windows Server 2008 R2系统无法远程连接登陆初步排查

    点左上角“发送远程命令”,选择“Ctrl-Alt-Delete”,使服务器当前界面进入到输密码的界面;

    夏日萤火
  • 前端,Java,产品经理,微信小程序,Python等资源合集大放送

    祈澈菇凉
  • 谁用了22号端口,到底是谁

    通常情况下一般使用netstat -aunltp 查看服务器连接状态信息,windows 和 linux 都能使用,大家都也熟悉

    蒋小爱
  • 抛弃console.log(),拥抱浏览器Debugger

    为了保证可读性,本文采用意译而非直译。另外,本文版权归原作者所有,翻译仅用于学习。

    Fundebug
  • 【腾讯云的1001种玩法】构建企业级应用环境之应用层面优化

    在上一篇中,我们完成了数据区域的优化,得到很多童鞋的反馈,说想了解下如何优化应用层面,其实也无所谓优化,之前我们在实现应用高可用时采用的是NLB 或 IIS A...

    李斯达
  • 智慧城市解决方案

    智慧城市不只是个集成平台,而是能够让用户在这个平台里,要自己想要的,删除自己不需要的,深度为用户考虑,集成功能以后,怎么用的更舒服,得到更好的体验,是我们重要考...

    中云微迅

扫码关注云+社区

领取腾讯云代金券

玩转腾讯云 有奖征文活动