语义分割论文：Fully Convolutional Networks for Semantic Segmentation (CVPR2015)

FCN:
Fully Convolutional Networks for Semantic Segmentation (CVPR2015)
https://arxiv.org/pdf/1411.4038.pdf
PyTorch: https://github.com/shanglianlm0525/SemanticSegmentation-network

第一篇将CNN引入image segmentation 的文章，提出了一种end-to-end的做semantic segmentation的方法。

特点：
a) 将之前分类网络的全连接层都换成卷积层；
b) 使用上采样操作,上采样的参数是可学习的，这里采用的方法是反卷积；
c) 将这些特征图进行上采样之后，将特征图对应元素相加；
　　因为经过多次卷积和pooling之后，得到的图像越来越小，分辨率越来越低，FCN为了得到信息，使用上采样（使用deconvolution）实现尺寸还原。不仅对pool5之后的特征图进行了还原，也对pool4和pool3之后的特征图进行了还原，结果表明，从这些特征图能很好的获得关于图片的语义信息，而且随着特征图越来越大，效果越来越好。

PyTorch代码:

import torch
import torch.nn as nn
import torchvisionclass FCN8s(nn.Module):def __init__(self, num_classes):super(FCN8s, self).__init__()vgg = torchvision.models.vgg16()features = list(vgg.features.children())self.padd = nn.ZeroPad2d([100,100,100,100])self.pool3 = nn.Sequential(*features[:17])self.pool4 = nn.Sequential(*features[17:24])self.pool5 = nn.Sequential(*features[24:])self.pool3_conv1x1 = nn.Conv2d(256, num_classes, kernel_size=1)self.pool4_conv1x1 = nn.Conv2d(512, num_classes, kernel_size=1)self.output5 = nn.Sequential(nn.Conv2d(512, 4096, kernel_size=7),nn.ReLU(inplace=True),nn.Dropout(),nn.Conv2d(4096, 4096, kernel_size=1),nn.ReLU(inplace=True),nn.Dropout(),nn.Conv2d(4096, num_classes, kernel_size=1),)self.up_pool3_out = nn.ConvTranspose2d(num_classes, num_classes, kernel_size=16, stride=8)self.up_pool4_out = nn.ConvTranspose2d(num_classes, num_classes, kernel_size=4, stride=2)self.up_pool5_out = nn.ConvTranspose2d(num_classes, num_classes, kernel_size=4, stride=2)def forward(self, x):_,_, w, h = x.size()x = self.padd(x)pool3 = self.pool3(x)pool4 = self.pool4(pool3)pool5 = self.pool5(pool4)output5 = self.up_pool5_out(self.output5(pool5))pool4_out = self.pool4_conv1x1(0.01 * pool4)output4 = self.up_pool4_out(pool4_out[:,:,5:(5 + output5.size()[2]) ,5:(5 + output5.size()[3])]+output5)pool3_out = self.pool3_conv1x1(0.0001 * pool3)output3 = self.up_pool3_out(pool3_out[:, :, 9:(9 + output4.size()[2]), 9:(9 + output4.size()[3])] + output4)out = self.up_pool3_out(output3)out = out[:, :, 31: (31 + h), 31: (31 + w)].contiguous()return outif __name__ == '__main__':model = FCN8s(num_classes=20)print(model)input = torch.randn(1,3,224,224)output = model(input)print(output.shape)

语义分割论文：Fully Convolutional Networks for Semantic Segmentation (CVPR2015)相关推荐

全卷积网络的理解——理解论文Fully Convolutional Networks for Semantic Segmentation
目录论文详解 1.和VGG网络的对比 2.那么fcn是什么? 3.论文改进的模型 3.1怎样进行上采样的问题 3.2从哪里开始上采样的问题--跳跃连接的问题 3.3整体设计思想 4.1实验结果 4. ...
论文笔记（FCN网络，语义分割）：Fully Convolutional Networks for Semantic Segmentation
FCN论文笔记:Fully Convolutional Networks for Semantic Segmentation 语义分割模型结构时序: FCN SegNet Dilated Convol ...
Fully Convolutional Networks for Semantic Segmentation (FCN)论文翻译和理解
论文题目:Fully Convolutional Networks for Semantic Segmentation 论文来源:Fully Convolutional Networks for Se ...
论文精读及分析：Fully Convolutional Networks for Semantic Segmentation
本文主要内容为论文<Fully Convolutional Networks for Semantic Segmentation> 的阅读笔记,在原始论文的基础上加入了自己的一些理解, ...
【论文翻译】Fully Convolutional Networks for Semantic Segmentation
论文题目:Fully Convolutional Networks for Semantic Segmentation 论文来源:Fully Convolutional Networks for Se ...
【论文笔记】FCN：Fully Convolutional Networks for Semantic Segmentation
<Fully Convolutional Networks for Semantic Segmentation>,CVPR 2015 文章目录 1. 概览 2. 主要亮点 2.1 全卷积化 ...
论文笔记《Fully Convolutional Networks for Semantic Segmentation》
[论文信息] <Fully Convolutional Networks for Semantic Segmentation> CVPR 2015 best paper key word: ...
Fully Convolutional Networks for Semantic Segmentation ————全卷积网络 FCN论文解读
Fully Convolutional Networks for Semantic Segmentation 作者: Jonathan Long, Evan Shelhamer, Trevor Dar ...
(FCN)-Fully Convolutional Networks for Semantic Segmentation
文章目录 Fully Convolutional Networks for Semantic Segmentation 摘要全局信息和局部信息感受野 FCN算法架构训练技巧详细参考 Fully ...
【FCN】Fully Convolutional Networks for Semantic Segmentation学习
论文翻译又是一个看不懂原文,又看不懂翻译的论文. semantic segmentation 图像语义分割就是预测每个像素所属的对象类别语义分割是指像素级地识别图像,即标注出图像中每个像素所属的 ...

语义分割论文：Fully Convolutional Networks for Semantic Segmentation (CVPR2015)

语义分割论文：Fully Convolutional Networks for Semantic Segmentation (CVPR2015)相关推荐

最新文章

热门文章