语义分割--Large Kernel Matters--Improve Semantic Segmentation by Global Convolutional Network
来源:互联网 发布:mac os 显示内容放大 编辑:程序博客网 时间:2024/05/16 05:09
Large Kernel Matters–Improve Semantic Segmentation by Global Convolutional Network
https://arxiv.org/abs/1703.02719
语义分割问题需要同时解决两个问题:classification 和 localization, 将图像中的每个物体精确分割出来,同时对每个物体进行分类。分类和定位这两个问题对于CNN 设计要求有所区别。
For the classification task, the models are required to be invariant to various transformations like translation and rotation.
But for the localization task, models should be transformation-sensitive, i.e., precisely locate every pixel for each semantic category
当前的语义分割算法主要侧重于 localization , which may be suboptimal for classification
怎么解决这个contradictory 了? 这里我们的策略是使用 Large Kernel
这里我们设计了一个 Global Convolutional Network 采用 Large Kernel
from the localization view, the structure must be fully-convolutional without any fully-connected layer or global pooling layer that used by many classification networks,since the latter will discard localization information
from the classification view, motivated by the densely-connected structure of classification models, the kernel size of the convolutional structure should be as large as possible.
对于 GCN 模块计算量问题: Instead of directly using larger kernel or global convolution, our GCN module employs a
combination of 1 × k + k × 1 and k × 1 + 1 × k convolutions, which enables densely connections within a large k×k region inthe feature map.
为了提升物体边缘分割精度,提出Boundary Refinement
we propose a Boundary Refinement (BR) block shown in Figure 2 C. Here, we models the boundary alignment as a residual structure.
Kernal 尺寸越大,效果越好
GCN 与其他两个convolution结构 对比:
上面三个图主要证明 GCN 效果比其他卷积结构好
PASCAL VOC 2012 test set
Cityscapes test set
- 语义分割--Large Kernel Matters--Improve Semantic Segmentation by Global Convolutional Network
- 旷视最新-Large Kernel Matters —— Improve Semantic Segmentation by Global Convolutional Network
- Large Kernel Matters —— Improve Semantic Segmentation by Global Convolutional Network论文阅读
- 【图像语义分割】Large Kernel Maters--Improved Semantic Segmentation by Global ConvNet
- Semantic Segmentation --Improve Semantic Segmentation by Global Convolutional Network(GCN)论文解读
- 语义分割--Fully Convolutional DenseNets for Semantic Segmentation
- 【图像语义分割】Fully Convolutional Networks for Semantic Segmentation
- 语义分割--Global Deconvolutional Networks for Semantic Segmentation
- 语义分割--DeconvNet--Learning Deconvolution Network for Semantic Segmentation
- 语义分割DeepLab v2--DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolut
- 用于语义分割的全卷积网络 (fully convolutional networks for semantic segmentation)
- 语义分割--Understanding Convolution for Semantic Segmentation
- 语义分割(Semantic Segmentation )论文
- 语义分割--Label Refinement Network for Coarse-to-Fine Semantic Segmentation
- 《Fully Convolutional Network for Semantic Segmentation》的阅读分享
- 【图像分割】Fully Convolutional Networks for Semantic Segmentation
- 图像分割“Fully Convolutional Networks for Semantic Segmentation”
- 深度图像分割 -- Fully Convolutional Networks for Semantic Segmentation
- 搭建Elasticsearch 5.4分布式集群
- Java判断IP为局域网(内网)IP
- caffe 绘制网络模型图
- 使用真机进行测试
- Tomcat端口号被占用问题
- 语义分割--Large Kernel Matters--Improve Semantic Segmentation by Global Convolutional Network
- Maven 之 profile
- s5pv210——LCD的原理和实战
- LinuxC语言实现下载功能(curl)
- Android中调用第三方打开本地doc、pdf、ppt、text等文件功能的实现
- QT 剪贴板 QClipboard 打开文件夹 openUrl
- Codeforces 600E Lomsat gelral 树上启发式合并
- SpringTest框架整合JUnit单元测试两种方式
- solution of my error