Paper Reading: Perceptual Generative Adversarial Networks for Small Object Detection
Perceptual Generative Adversarial Networks for Small Object Detection
2017-07-11 19:47:46 CVPR 2017
This paper use GAN to handle the issue of small object detection which is a very hard problem in general object detection. As shown in the following figures, small object and large objects usually shown different representations from the feature level.
Thus, it is possbile to use Percetual GAN to super-resolution of feature maps of small objects to obtain better detection performance.
It consists of two subnetworks, i.e., a generator network and a perceptual discriminator network. Specifically, the generator is a deep residual based feature generative model which transforms the original poor features of small objects to highly discriminative ones by introducing fine-grained details from lower-level layers, achieving “super-resolution” on the intermediate representations.
Different from normal GAN, this network also introduce a new perceptual loss tailored from the detection purpose. That is to say, the discriminator not only need to deal with the adversarial loss, but also need to justify the detection accuray benefiting from the generated super-resolved features with a perceptual loss.
The proposed contributions:
(1) We are the first to successfully apply GAN-alike models to solve the challenging small-scale object detection problems.
(2) We introduce a new conditional generator model that learns the additive residual representation between large and small objects, instead of generating the complete representations as before.
(3) We introduce a new perceptual discriminator that provides more comprehensive supervision beneficial for detections, instead of barely differentiating fake and real.
(4) Successful applications on traffic sign detection and pedestrian detection have been achieved with the state-of-the-art performance.
Figure 2. Training procedure of object detection network based on the Perceptual GAN.
As shown in Figure 2, the generator network aims to generate super-resoved representation for the small object.
The discriminator includes two branches, i.e.
1. the adversarial branch for differentiating between the generated superresolved representation.
2. the perception branch for justifying the detection accurcy benefiting from the generation representation.
==>> Dicriminative Network Architecture:
The D network need to justify the dection accuracy benefiting from the generated super-resovled feature.
Given the adversarial loss $L_{dis_a}$ and the perceptual loss $L_{dis_p}$ , a final loss function Ldis can be produced as weighted sum of both individual loss components. Given weighting parameters w1 and w2, we define Ldis = w1 × Ldis_a + w2 × Ldis_p to encourage the generator network to generate super-resolved representation with high detection accuracy. Here we set both w1 and w2 to be one.
Paper Reading: Perceptual Generative Adversarial Networks for Small Object Detection的更多相关文章
- 【文献阅读】Perceptual Generative Adversarial Networks for Small Object Detection –CVPR-2017
Perceptual Generative Adversarial Networks for Small Object Detection 2017CVPR 新鲜出炉的paper,这是针对small ...
- Perceptual Generative Adversarial Networks for Small Object Detection
Perceptual Generative Adversarial Networks for Small Object Detection 感知生成对抗网络用于目标检测 论文链接:https://ar ...
- (转)Introductory guide to Generative Adversarial Networks (GANs) and their promise!
Introductory guide to Generative Adversarial Networks (GANs) and their promise! Introduction Neural ...
- 论文笔记之:UNSUPERVISED REPRESENTATION LEARNING WITH DEEP CONVOLUTIONAL GENERATIVE ADVERSARIAL NETWORKS
UNSUPERVISED REPRESENTATION LEARNING WITH DEEP CONVOLUTIONAL GENERATIVE ADVERSARIAL NETWORKS ICLR 2 ...
- Generative Adversarial Networks overview(2)
Libo1575899134@outlook.com Libo (原创文章,转发请注明作者) 本文章会先从Gan的简单应用示例讲起,从三个方面问题以及解决思路覆盖25篇GAN论文,第二个大部分会进一步 ...
- Generative Adversarial Networks overview(1)
Libo1575899134@outlook.com Libo (原创文章,转发请注明作者) 本文章会先从Gan的简单应用示例讲起,从三个方面问题以及解决思路覆盖25篇GAN论文,第二个大部分会进一步 ...
- GD-GAN: Generative Adversarial Networks for Trajectory Prediction and Group Detection in Crowds
GD-GAN: Generative Adversarial Networks for Trajectory Prediction and Group Detection in Crowds 2019 ...
- Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks
Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks 2019-06-01 09:52:4 ...
- 文献阅读报告 - Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks
paper:Gupta A , Johnson J , Fei-Fei L , et al. Social GAN: Socially Acceptable Trajectories with Gen ...
随机推荐
- Teacher Bo (时间复杂度 + 暴力)
如果你仔细看就会发现有一个数据很重要那就是点的范围,那么这样一来最多只有2 * maxn的不同曼哈顿距离了,这样一看只要暴力一下就可以过了. #include<bits/stdc++.h> ...
- skynet 报错 skynet 服务缺陷 Lua死循环
我的报错如下: 看起来是skynet中lua死循环,实际上,可能只是本地配置出了问题,比如,我的数据库连接不上了,因为我把别人的配置更新到我本地了,吗,mysql秘密不对 解决办法就是将配置文件中的, ...
- mysql 安装目录说明
- HIBERNATE与 MYBATIS的对比
我是一名java开发人员,hibernate以及mybatis都有过学习,在java面试中也被提及问道过,在项目实践中也应用过,现在对hibernate和mybatis做一下对比,便于大家更好的理解和 ...
- JAVA基础3---JVM内存模型
Java虚拟机执行Java程序的时候需要使用一定的内存,根据不同的使用场景划分不同的内存区域.有公用的区域随着Java程序的启动而创建:有线程私有的区域依赖线程的启动而创建 JVM内存模型大致可以分为 ...
- JustOj 1929: 多输入输出练习1
题目描述 给定很多行数据,要求输出每一行的最大值. 输入 程序有多行输入,每一行以0结束. 输出 有多行输出,对应输入的行数. 样例输入 23 -456 33 78 0 43 23 987 66 -1 ...
- sass中的循环判断条件语句
@if $lte7:true !default;//是否兼容ie6,7 //inline-block //ie6-7 *display: inline;*zoom:1; @mixin inline-b ...
- 前端框架VUE----cli脚手架(框架)
一.创建vue项目 npm install vue-cli -g #-g全局 (sudo)npm install vue-cli -g #mac笔记本 vue-init webpack myvue # ...
- checkbox 全选效果
html部分 <p id="all">全选</p> <input type="checkbox" /><br/> ...
- 隐藏域传值到后台controller
开发背景:一个页面有一个下拉框和一个单选按钮,下拉框保存的是厂商信息,单选按钮保存的是产品信息.每次下拉框的内容被选中,把厂商编码保存到隐藏域 <input type="hidden& ...