Weakly Supervised Deep Detection Networks 阅读笔记
来源:互联网 发布:主力资金数据 编辑:程序博客网 时间:2024/06/14 07:35
Weakly Supervised Deep Detection Networks 阅读笔记
Overall architecture
1. Existing network(such as AlexNet pre-trained on ImageNet)
2. SPP --> region level descriptor
3. (1) class score --> recognition
(2) probability distribution(which region contains the most salient image structure) --> detection
4. aggregate the recognition and detection scores to predict the class of image(image level supervision)
Compared with other method
1. MIL: Use the appearance model itself to perform region selection
WSDDN: detection branch is independent of recognition branch
2. Bilinear architecture: two streams are symmetric
WSDDN: detection branch is explicitly designed
Method
1. Pre-trained network
2. Weakly supervised deep detection network
(1) Region level descriptor:
Region proposal: SSW, EB
(2) Classification data stream: fc + softmax
(3) Detection data stream: fc + softmax(differently defined)
(4) Combined region scores and detection
Final score of each region:
Then rank regions for each class independently.
Then apply nms(0.4)
(5) Image-level classification scores
Image level class score:
(yc in (0, 1))
Softmax is not applied because one image can have multiple label
3. Training WSDDN
A collection of images xi, i=1, 2, … , n
Image level labels yi∈ {-1, 1}C
4. Spatial regulariser
Penalize the feature map discrepancies between the highest scoring region and the regions with at least 60% IoU during training.
Experiments
CorLoc: the percentage of images that contain at least one instance of the target object class for which the most confident detected bounding box overlaps by at least 0.5 with one of these instances.
Problem: (1) group multiple object instances with a single bounding box
(2)focus on parts rather than the whole object
Result:
- Weakly Supervised Deep Detection Networks 阅读笔记
- 论文笔记:Weakly Supervised Deep Detection Networks
- READING NOTE: Weakly Supervised Cascaded Convolutional Networks
- Weakly Supervised Object Recognition with Convolutional Neural Networks
- Weakly supervised object recognition with convolutional neural networks 论文解读
- 《Deep Self-Taught Learning for Weakly Supervised Object Localization》
- 论文阅读:Deep Neural Networks for Object Detection
- Large Scale Distributed Deep Networks 阅读笔记
- 【论文笔记】Scalable Object Detection using Deep Neural Networks
- 【深度学习论文笔记】Deep Neural Networks for Object Detection
- 论文笔记 《Deep Neural Networks for Object Detection》
- 论文笔记《Deep Neural Networks for Object Detection》
- 【论文笔记】Deep Neural Networks for Object Detection
- Scalable Object Detection using Deep Neural Networks笔记
- Supervised Deep Learning with Auxiliary Networks
- 论文阅读笔记:Object Detection Networks on Convolutional Feature Maps
- Feature Pyramid Networks for Object Detection 阅读笔记
- 目标定位--Deep Self-Taught Learning for Weakly Supervised Object Localization
- LeetCode27. Remove Element
- HDOJ HDU 2602 Bone Collector
- Leetcode 40. Combination Sum II
- R语言read.xlsx( )函数报错 LoadLibrary failure: %1 不是有效的 Win32 应用程序
- 时间模块和类
- Weakly Supervised Deep Detection Networks 阅读笔记
- 进程与线程
- 你了解泰尔实验室和泰尔认证中心吗?
- SparkML(二) 设计机器学习系统
- 莫比乌斯进阶:bzoj 3994 约数个数和(Mobius)
- 跟我一起写 Makefile(一)
- B树和B+树的区别
- 设计模式——装饰模式
- RedHat Linux网络配置详解