Reading Note: Deformable Part-based Fully Convolutional Network for Object Detection
来源:互联网 发布:淘宝卖家改地址 编辑:程序博客网 时间:2024/05/17 00:08
TITLE: Deformable Part-based Fully Convolutional Network for Object Detection
AUTHOR: Taylor Mordan, Nicolas Thome, Matthieu Cord, Gilles Henaff
FROM: arXiv:1707.06175
CONTRIBUTIONS
- Deformable Part-based Fully Convolutional Network (DPFCN), an end-to-end model integrating ideas from DPM into region-based deep ConvNets for object detection, is proposed.
- A new deformable part-based RoI pooling layer is introduced, which explicitly selects discriminative elements of objects around region proposals by simultaneously optimizing latent displacements of all parts.
- Another improvement is the design of a deformation-aware localization module, a specific module exploiting configuration information to refine localization.
METHOD
R-FCN is the work closest to DP-FCN. Both are developed on the basis of Faster-RCNN, in which an RPN is used to generate object proposals and a designed pooling layer is used to extract features for classification and localization. The architecture of DP-FCN is illustrated in the following figure. A Deformable part-based RoI Pooling layer follows a FCN network. Then two branches predict category and location respectively. The output of the backbone FCN is similar to that in R-FCN. It has
Deformable part-based RoI pooling
For each input channel, just like what has been done in DPM, a transformation is carried out to spread high responses to nearby locations, taking into account the deformation costs.
In my understanding, the output of RPN works like the root filter in DPM. Then the region proposal is evenly divided into
Classification and localization predictions with deformable parts
Predictions are performed with two sibling branches for classification and relocalization of region proposals as is common practice. The classification branch is simply composed of an average pooling followed by a SoftMax layer.
As for location prediction, every part has 4 elements to be predicted. In addition to that, the displacement is sent to two fully connected layers and is then element-wise multiplied with the first values to yield the final localization output for this class.
- Reading Note: Deformable Part-based Fully Convolutional Network for Object Detection
- 论文阅读-《Deformable Part-based Fully Convolutional Network for Object Detection》
- READING NOTE: R-FCN: Object Detection via Region-based Fully Convolutional Networks
- READING NOTE: R-FCN: Object Detection via Region-based Fully Convolutional Networks
- READING NOTE: SuperCNN: A Superpixelwise Convolutional Neural Network for Salient Object Detection
- 论文笔记:R-FCN: Object Detection via Region-based Fully Convolutional Network
- DeepID-Net:multi-stage and deformable deep convolutional neural network for object detection
- R-FCN: Object Detection via Region-based Fully Convolutional Networks
- R-FCN: Object Detection via Region-based Fully Convolutional Networks
- R-FCN: Object Detection via Region-based Fully Convolutional Networks
- R-FCN: Object Detection via Region-based Fully Convolutional Networks
- R-FCN: Object Detection via Region-based Fully Convolutional Networks
- R-FCN: Object Detection via Region-based Fully Convolutional Networks
- R-FCN: Object Detection via Region-based Fully Convolutional Networks
- Object Contour Detection with a Fully Convolutional Encoder-Decoder Network
- READING NOTE:LCNN: Lookup-based Convolutional Neural Network
- [论文阅读]R-FCN: Object Detection via Region-based Fully Convolutional Networks
- 论文笔记 | R-FCN: Object Detection via Region-based Fully Convolutional Networks
- C++ lambda 表达式
- osg::Geomtery多图元重叠闪烁问题
- 11.编写COM常用IDL指令和注意事项详解
- tensorflow学习1
- 文本处理工具
- Reading Note: Deformable Part-based Fully Convolutional Network for Object Detection
- Leetcode98. Validate Binary Search Tree
- SOD923/SOD523/SOD323封装是多大?
- HRBEU-贪心,区间-A公司的烦恼
- 冲突域、广播域,划分VLAN的缘由
- Maven学习总结(三)——手动将本地jar导入仓库
- mysql计数器表
- 关于SPECJbb2005
- hdu 1109 Run Away