[paper reading] C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object Detectio
MIL陷入局部最优，检测到局部，没法完整的检测到物体。将instance划分为空间相关和类别相关的子集。在这些子集中定义一系列平滑的损失近似代替原损失函数，优化这些平滑损失。app
C-MIL learns instance subsets, where the instances are spatially related, i.e., overlapping with each other, and class related, i.e., having similar object class scores.函数
C-MIL treats images as bags and image regions generated by an object proposal method [24,32] as instances优化
待解决的问题：spa
1) How to optimize the non-convex function.net
2) How to perform instance selection in the early training stages when the instance selector is not well trained.3d
to be continue ...orm
更完整的论文笔记[csdn]blog
相关文章
- 1. 论文笔记（五） C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object Detection
- 2. 【paper reading】《Proposal learning for semi-supervised object detection》
- 3. Two-Phase Learning for Weakly Supervised Object Localization
- 4. Deep Self-Taught Learning for Weakly Supervised Object Localization
- 5. 《Deep Self-Taught Learning for Weakly Supervised Object Localization》
- 6. 论文解读：Object Instance Mining for Weakly Supervised Object Detection（AAAI 2020）
- 7. 简读：Object-Aware Instance Labeling for Weakly Supervised Object Detection
- 8. Object Instance Mining for Weakly Supervised Object Detection 论文笔记
- 9. [CVPR2015] Is object localization for free? – Weakly-supervised learning with convolutional neural n...
- 10. [CVPR2015] Is object localization for free? – Weakly-supervised learning with convolutional neural n
- 更多相关文章...
- • Scala for循环 - Scala教程
- • Swift for 循环 - Swift 教程
- • Java Agent入门实战（三）-JVM Attach原理与使用
- • Java Agent入门实战（一）-Instrumentation介绍与使用
相关标签/搜索
每日一句
-
每一个你不满意的现在，都有一个你没有努力的曾经。
最新文章
- 1. python的安装和Hello，World编写
- 2. 重磅解读：K8s Cluster Autoscaler模块及对应华为云插件Deep Dive
- 3. 鸿蒙学习笔记2（永不断更）
- 4. static关键字 和构造代码块
- 5. JVM笔记
- 6. 无法启动 C/C++ 语言服务器。IntelliSense 功能将被禁用。错误: Missing binary at c:\Users\MSI-NB\.vscode\extensions\ms-vsc
- 7. 【Hive】Hive返回码状态含义
- 8. Java树形结构递归（以时间换空间）和非递归（以空间换时间）
- 9. 数据预处理---缺失值
- 10. 都要2021年了，现代C++有什么值得我们学习的？
欢迎关注本站公众号,获取更多信息
相关文章
- 1. 论文笔记（五） C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object Detection
- 2. 【paper reading】《Proposal learning for semi-supervised object detection》
- 3. Two-Phase Learning for Weakly Supervised Object Localization
- 4. Deep Self-Taught Learning for Weakly Supervised Object Localization
- 5. 《Deep Self-Taught Learning for Weakly Supervised Object Localization》
- 6. 论文解读：Object Instance Mining for Weakly Supervised Object Detection（AAAI 2020）
- 7. 简读：Object-Aware Instance Labeling for Weakly Supervised Object Detection
- 8. Object Instance Mining for Weakly Supervised Object Detection 论文笔记
- 9. [CVPR2015] Is object localization for free? – Weakly-supervised learning with convolutional neural n...
- 10. [CVPR2015] Is object localization for free? – Weakly-supervised learning with convolutional neural n