【论文笔记】Object Contour Detection with a Fully Convolutional Encoder-Decoder Network
来源:互联网 发布:前后端分离 知乎 编辑:程序博客网 时间:2024/06/08 17:40
Object Contour Detection with a Fully Convolutional Encoder-Decoder Network
使用卷积编码解码网络检测主要目标的边缘
网络结构是:
编码:VGG-16
解码:反池化-卷积-激活-dropout
卷积核:
The number of channels of every decoder layer is properly
designed to allow unpooling from its corresponding maxpooling layer.
dropout:
We also add a dropout layer after each relu layer in the decoder. A complete decoder network setup is listed in Table 1
损失函数:
loss function is simply the pixel-wise logistic loss.
反池化:
We initialize our encoder with VGG-16 net [48] (up to the “fc6” layer) and to achieve dense prediction of image size our decoder is constructed by alternating unpooling and convolution layers where unpooling layers re-use the switches from max-pooling layers of encoder to upscale the feature maps.
反池化细节:
http://blog.csdn.net/xiaxzhou/article/details/74012137
训练:
During training, we fix the encoder parameters (VGG-16) and only optimize decoder parameters.
- 【论文笔记】Object Contour Detection with a Fully Convolutional Encoder-Decoder Network
- Object Contour Detection with a Fully Convolutional Encoder-Decoder Network
- 论文笔记:R-FCN: Object Detection via Region-based Fully Convolutional Network
- 论文笔记 MSCNN:A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection
- 论文阅读-《Deformable Part-based Fully Convolutional Network for Object Detection》
- 论文笔记 | SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation
- [论文笔记]SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation
- 论文《A Convolutional Neural Network Cascade for Face Detection》笔记
- 【论文笔记】A Convolutional Neural Network Cascade for Face Detection
- 论文《A Convolutional Neural Network Cascade for Face Detection》笔记
- 论文《A Convolutional Neural Network Cascade for Face Detection》笔记
- 论文笔记 | R-FCN: Object Detection via Region-based Fully Convolutional Networks
- 论文笔记 R-FCN: Object Detection via Region-based Fully Convolutional Networks
- 【论文笔记】物体检测系列 R-FCN: Object Detection via Region-based Fully Convolutional Networks
- R-FCN: Object Detection via Region-based Fully Convolutional Networks 论文笔记
- 论文笔记 A MultiPath Network for Object Detection
- MSCNN 论文解析(A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection
- MSCNN 论文解析(A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection
- BZOJ 1086 王室联邦 树分块
- PAT乙级 1021. 个位数统计 (15)
- jsp中的4个作用范围
- SQL基础
- dubbo找不到dubbo.xsd,报错Multiple annotations found at this line:
- 【论文笔记】Object Contour Detection with a Fully Convolutional Encoder-Decoder Network
- 生成SSH key步骤标记
- 快速破解IntelliJ IDEA
- BP算法详解
- 微信小程序之购物车功能
- NP完全问题
- jquery源码解析
- Linux系统中对SSD硬盘优化的方法
- Java学习笔记-《Java程序员面试宝典》-第5章Java Web-5.2J2EE与EJB(5.2.11-5.2.16)