目标定位--Deep Self-Taught Learning for Weakly Supervised Object Localization
来源:互联网 发布:淘宝怎么查看购物车 编辑:程序博客网 时间:2024/06/05 16:55
Deep Self-Taught Learning for Weakly Supervised Object Localization
CVPR 2017
https://arxiv.org/abs/1704.05188
什么是 Weakly Supervised Object Localization,refers to learning to localize objects within images with only image-level annotations that simply indicate the presence of an object category.
也就是说我们的训练图像只有 针对图像的 注释,没有包含物体的矩形框,如下图所示
很明显这种弱监督学习要比有矩形框的学习难的多。目前的深度学习也应用到了这个问题。
本文的算法流程如下图所示:
3.1. Seed Sample Acquisition
3.1.1 Image-to-Object Transfer
这里的候选区域提取,我们使用了 文献【26】中的 Hypothesis-CNN-Pooling (HCP) 方法,
将图像中属于同一类物体的候选区域提取出来。
3.1.2 Reliable Seed Proposal Generation
有了若干候选区域,我们需要从中选择出一个最好的候选区域,这里我们使用了图论知识,将其表示为 dense subgraph discovery (DSD) problem
我们可以观察到,最好的候选区域位于同一个物体组成的节点网络的中心点位置。它的连接点最多。
3.2. Online Supportive Sample Harvesting
这一步是通过 Fast R-CNN 进一步得到 higher-quality positive samples。通过观察不同候选区域的 relative improvement (RI) of output CNN scores来自动找出最好的候选区域。
Bad seed samples hardly obtain RI from the increasing detection ability of Fast R-CNN during training. In contrast, high-quality positive samples not selected as seeds mostly gain RI due to the improved detection ability of the model. Therefore, RI is a reliable metric for identifying high-quality positive samples
坏的候选区域 对于 不断提高的Fast R-CNN ,其很难获得 RI
但是好的候选区域 对于 不断提高的Fast R-CNN, 可以得到 RI。
- 目标定位--Deep Self-Taught Learning for Weakly Supervised Object Localization
- 《Deep Self-Taught Learning for Weakly Supervised Object Localization》
- Two-Phase Learning for Weakly Supervised Object Localization
- 论文笔记《IS object localization for free? Weakly-supervised learning with convolutional neural network》
- Weakly Supervised Object Localization with Multi-fold Multiple Instance Learning
- Deep learning----------Self-taught learning
- 论文研读--Weakly Supervised Object Localization with Progressive Domain Adaptation
- 【Deep Learning】4、Self-Taught Learning
- Deep learning:十五(Self-Taught Learning练习)
- Deep learning:十五(Self-Taught Learning练习)
- Self-Taught Learning To Deep Networds
- Deep Learning by Andrew Ng --- self-taught
- Deep learning-------------Self-Taught Learning to Deep Networks
- Self-Taught Learning
- Learning Deep Features for Discriminative Localization
- Learning Deep Features for Discriminative Localization
- 论文笔记:Weakly Supervised Deep Detection Networks
- Weakly Supervised Deep Detection Networks 阅读笔记
- AngularJS绑定DOM
- 二叉树的镜像(Java实现)
- 股市中的黑五类
- python2.7.12以及其相关模块的安装
- 常见的排序算法
- 目标定位--Deep Self-Taught Learning for Weakly Supervised Object Localization
- DNS详解
- 该选择什么编程语言
- PS绘制边框
- python使用列表推导
- MFC中Cstring与char * string 的转换
- jq菜单切换demo
- TabLayout的使用
- centos 7.0 网络配置 和centos6.X 不同