语义分割--DeconvNet--Learning Deconvolution Network for Semantic Segmentation
2017-05-19 14:55
555 查看
Learning Deconvolution Network for Semantic Segmentation
ICCV2015
http://cvlab.postech.ac.kr/research/deconvnet/
https://devhub.io/zh/repos/myungsub-DeconvNet
本文提出了一个 deconvolution network 用于语义分割，还是针对 FCN 改善的。在pooling operation 记录 the locations of maximum activations ，将这些位置用于 unpooling
这一点和 SegNet 是一样的。
首先来说说FCN 有什么问题？
FCN 的 limitations：
1）FCN 因为其固定尺寸receptive field只能解决单尺度的semantics ，对于过大过小的目标分割都有可能有问题
the network can handle only a single scale semantics within image due to the fixed-size receptive field. Therefore, the object that is substantially larger or smaller than the receptive field may be fragmented or mislabeled.
2）FCN 的 deconvolution procedure 太粗糙太简单，FCN 的 deconvolution procedure输入尺寸只有16 × 16，将这个尺寸通过 bilinear interpolation 放大到输入图像尺寸。目标很多细节信息丢失
3 System Architecture
我们的网络包括两个部分：convolution and deconvolution networks
卷积网络用于提取特征，使用 VGG 16-layer net
convolution network corresponds to feature extractor
反卷积网络根据特征产生分割结果
deconvolution network is a shape generator that produces object segmentation from the feature extracted from the convolution network.
3.2. Deconvolution Network for Segmentation
反卷积网络中主要有两个操作步骤： unpooling and deconvolution
3.2.1 Unpooling
Pooling 会产生降采样的效果，导致一些细节丢失。 spatial information within a receptive field is lost during pooling，这些信息对于语义分割很重要。为了解决这个问题，我们在反卷积网络中使用 unpooling layers， It
records the locations of maximum activations selected during pooling operation in switch variables, which are employed to place each activation back to its original pooled location.
3.2.2 Deconvolution
unpooling layers 得到一个放大的但是稀疏的响应特征图， 这里通过deconvolution layers 来将稀疏的特征变为稠密的特征
The deconvolution layers densify the sparse activations obtained by unpooling through convolution-like operations with multiple learned filters.
The learned filters in deconvolutional layers correspond to bases to reconstruct shape of an input object.
Unpooling captures example-specific structures
learned filters in deconvolutional layers tend to capture class-specific shapes
与FCN 效果对比：
PASCAL VOC 2012 test set
instance-wise prediction 的好处
本文算法较FCN的细节要好些
FCN 的全局观要好一些
与FCN的结合
ICCV2015
http://cvlab.postech.ac.kr/research/deconvnet/
https://devhub.io/zh/repos/myungsub-DeconvNet
本文提出了一个 deconvolution network 用于语义分割，还是针对 FCN 改善的。在pooling operation 记录 the locations of maximum activations ，将这些位置用于 unpooling
这一点和 SegNet 是一样的。
首先来说说FCN 有什么问题？
FCN 的 limitations：
1）FCN 因为其固定尺寸receptive field只能解决单尺度的semantics ，对于过大过小的目标分割都有可能有问题
the network can handle only a single scale semantics within image due to the fixed-size receptive field. Therefore, the object that is substantially larger or smaller than the receptive field may be fragmented or mislabeled.
2）FCN 的 deconvolution procedure 太粗糙太简单，FCN 的 deconvolution procedure输入尺寸只有16 × 16，将这个尺寸通过 bilinear interpolation 放大到输入图像尺寸。目标很多细节信息丢失
3 System Architecture
我们的网络包括两个部分：convolution and deconvolution networks
卷积网络用于提取特征，使用 VGG 16-layer net
convolution network corresponds to feature extractor
反卷积网络根据特征产生分割结果
deconvolution network is a shape generator that produces object segmentation from the feature extracted from the convolution network.
3.2. Deconvolution Network for Segmentation
反卷积网络中主要有两个操作步骤： unpooling and deconvolution
3.2.1 Unpooling
Pooling 会产生降采样的效果，导致一些细节丢失。 spatial information within a receptive field is lost during pooling，这些信息对于语义分割很重要。为了解决这个问题，我们在反卷积网络中使用 unpooling layers， It
records the locations of maximum activations selected during pooling operation in switch variables, which are employed to place each activation back to its original pooled location.
3.2.2 Deconvolution
unpooling layers 得到一个放大的但是稀疏的响应特征图， 这里通过deconvolution layers 来将稀疏的特征变为稠密的特征
The deconvolution layers densify the sparse activations obtained by unpooling through convolution-like operations with multiple learned filters.
The learned filters in deconvolutional layers correspond to bases to reconstruct shape of an input object.
Unpooling captures example-specific structures
learned filters in deconvolutional layers tend to capture class-specific shapes
与FCN 效果对比：
PASCAL VOC 2012 test set
instance-wise prediction 的好处
本文算法较FCN的细节要好些
FCN 的全局观要好一些
与FCN的结合
内容来自用户分享和网络整理，不保证内容的准确性，如有侵权内容，可联系管理员处理 
相关文章推荐
- 【DeconvNet】Learning Deconvolution Network for Semantic Segmentation
- DeconvNet：Learning Deconvolution Network for Semantic Segmentation
- Learning Deconvolution Network for Semantic Segmentation
- 【论文笔记】Learning Deconvolution Network for Semantic Segmentation
- Learning Deconvolution Network for Semantic Segmentation
- Learning Deconvolution Network for Semantic Segmentation
- 深度学习论文笔记（七）---Deconvolution network-2016年（Learning Deconvolution Network for Semantic Segmentation ）
- Learning Deconvolution Network for Semantic Segmentation
- READING NOTE: Learning Deconvolution Network for Semantic Segmentation
- 语义分割--Label Refinement Network for Coarse-to-Fine Semantic Segmentation
- 语义分割--Deep Dual Learning for Semantic Image Segmentation
- 语义分割--Learning Object Interactions and Descriptions for Semantic Image Segmentation
- [深度学习论文笔记][Semantic Segmentation] Learning Deconvolution Network for Semantic Segmentation
- Learning Deconvolution Network for Semantic Segmentation
- 语义分割--RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation
- 语义分割--Full-Resolution Residual Networks for Semantic Segmentation in Street Scenes
- CNN for Semantic Segmentation（语义分割，论文，代码，数据集，标注工具，blog）
- CNN for Semantic Segmentation（语义分割，论文，代码，数据集，标注工具，blog）
- 语义分割 DeepLabv3--Rethinking Atrous Convolution for Semantic Image Segmentation
- 语义分割--LinkNet: Exploiting Encoder Representations for Efficient Semantic Segmentation