反卷积(Deconvolution)上采样(Upsampling)上池化(Unpooling)的区别—

http://blog.csdn.net/u012949263/article/details/54379996 提供了英文版

Question：

Deconvolution networks use deconvolution layers to infer sparse feature maps and filters (this is the same as convolutional sparse coding).

In the context of Fully Convolutional Networks that perform pixel-wise segmentation, does deconvolution just mean upsampling (e.g. bilinear interpolation)? Is this is different to deconvolutional layers in Deconv Nets?

As far as I understand unpooling just mean using switches to position values in the switch positions with the rest of the values in between set to zero?

It would be great if someone could clarify the differences between these terms.

2 Answers：

Christian Baumgartner
Christian Baumgartner, 5 years of experience in using machine learning for medical image analysis
Written Nov 10
Upsampling refers to any technique that, well, upsamples your image to a higher resolution.

The easiest way is using resampling and interpolation. This is taking an input image, rescaling it to the desired size and then calculating the pixel values at each point using a interpolation method such as bilinear interpolation.

Unpooling is commonly used in the context of convolutional neural networks to denote reverse max pooling. Citing from this paper: Unpooling: In the convnet, the max pooling operation is non-invertible, however we can obtain an approximate inverse by recording the locations of the maxima within each pooling region in a set of switch variables. In the deconvnet, the unpooling operation uses these switches to place the reconstructions from the layer above into appropriate locations, preserving the structure of the stimulus.

Deconvolution in the context of convolutional neural networks is often used to denote a sort of reverse convolution, which importantly and confusingly is not actually a proper mathematical deconvolution. In contrast to unpooling, using ‘deconvolution’ the upsampling of an image can be learned. It is often used for upsampling the output of a convnet to the original image resolution. I wrote another answer on this topic here. Deconvolution is more appropriately also referred to as convolution with fractional strides, or transpose convolution.

Then there is proper deconvolution which reverses the effect of a convolution (Deconvolution - Wikipedia). I don’t think people actually use this in the context of convolutional neural networks.

I don’t know much about convolutional sparse coding but it appears to me from glancing at a few papers, that those approaches use of the former kind of ‘deconvolution’, i.e. tranpose convolution, to allow you to go from a sparse image representation obtained using convnets, back to the original image resolution. (Happy to be corrected on this.)

对解答拙劣地翻译一发：

上采样是指将图像上采样到更高分辨率的任何技术。
最简单的方法是使用重新采样和插值。即取原始图像输入，将其重新缩放到所需的大小，然后使用插值方法（如双线性插值）计算每个点处的像素值。

在CNN上下文中，上池化通常指代最大池化的逆过程。在CNN中，最大池化操作是不可逆的，但是我们可以通过使用一组转换变量记录每个池化区域内最大值的位置来获得一个近似的逆操作结果。在反卷积（网络）中，上池化操作使用这些转换变量从前一层输入中安放这些复原物到（当前层）合适的位置，从而一定程度上保护了原有结构。

在CNN上下文中，反卷积通常用于指代卷积的逆过程，而非数学意义上真正的反卷积，这一点很重要，也很令人困惑。相比上池化，使用反卷积进行图像的上采样是可以被学习的。反卷积常被用于对CNN的输出进行上采样至原始图像分辨率。我在这里写下关于这个问题的另一个答案：

反卷积常被认为是空洞卷积或者转置卷积，这也更为恰当一些。

对于一个卷积，存在一个合适的反卷积反转/消除它的影响/作用（反卷积 - 维基百科）。我不认为人们实际上在CNN上下文中使用这个（定义）。

我对卷积稀疏编码知之甚少，但在浏览一些论文的过程中我发现，这些论文使用了前一种“反卷积”，即转置卷积，使图像从卷积生成的稀疏图像表示回到原始图像分辨率。（很高兴这一点能够被纠正。）

翻译水平有限，如有误请斧正。

由于上采样是指将图像上采样到更高分辨率的任何技术，因此我们可以讲：通过反卷积进行上采样。

反卷积(Deconvolution)上采样(Upsampling)上池化(Unpooling)的区别——附翻译相关推荐

深度可分离卷积、空洞卷积、反卷积、感受野计算、上采样
文章目录输出特征图尺寸的计算 Depthwise卷积和Pointwise运算成本比较低空洞卷积反卷积上采样输出特征图尺寸的计算 Depthwise卷积和Pointwise运算成本比较低如何 ...
反卷积(Deconvolution)、上采样(UNSampling)与上池化(UnPooling)加入自己的思考（pytorch函数）（二）
ps之前写过反卷积(Deconvolution).上采样(UNSampling)与上池化(UnPooling)加入自己的思考(一),不过那是东拼西凑出来的别人的东西就是稍微加入点自己的理解.今天在看代 ...
反卷积(Deconvolution)、上采样(UNSampling)与上池化(UnPooling)加入自己的思考（tensorflow函数）（一）
ps 之前是做分类的根本就是没有很深的接触反卷积(Deconvolution).上采样(UNSampling)与上池化(UnPooling)等,要写这个主要是我在找unet代码时候发现反卷积这一步正常 ...
图像语义分割中的上采样(Upsampling)和下采样(subsampling)
图像语义分割中的上采样和下采样 1. 下采样(subsampled) 2. 上采样(upsampled) 2.1 线性插值 2.2 单线性插值 2.3 双线性插值 2.4 双线性插值举例 2.5 插值 ...
反卷积算法 c语言,多次曝光图像的PSF反卷积以及欠采样图像的反混叠技术I：PSFdeLRSA的制作方法...
1技术领域在图像的点扩散函数(PSF)反卷积领域,人们发展了很多方法:比如基于最大似然估计的Lucy-Richardson图像PSF反卷积技术和在该技术基础上加入的正则化手段,比如基于最小均方差或最 ...
卷积层，池化层，padding=‘same‘ ，为什么卷积层图像尺寸不变，池化层后图像尺寸减半呢？
先摆一下通用计算公式: h:图像长度,k:卷积/池化核尺寸,p:填充数,s:移动步长长度公式: 宽度公式: 对于经过卷积,池化后的图像尺寸都可以按照此公式进行计算. 在实际的使用过程中经常会有此疑惑 ...
反卷积(Deconvolution)、上采样(UNSampling)与上池化(UnPooling)加入自己的思考（pytorch函数）（三）
ps:最近在做分割在github上找代码看模型时老发现尺度从小到大那部分,有的是采用上采样(双线性插值)+卷积,有的用反卷积.为什么不相同能,我查阅相关资料发现这位知乎大神根据外网大佬文章总结原因.知 ...
上采样(upsampling)方法总结
总结一下上采样,主要来源于论文<Deep Learning for Image Super-resolution:A Survey> 上采样层位置上采样方法 2.1预定义插值式最近邻插 ...
卷积神经网络---卷积层、激励层、池化层以及全连接层
文章目录概述卷积神经网络局部连接+权值共享** 输入层卷积层激励层池化层全连接层参考资料概述这两天在看论文,涉及到卷积神经网络的知识,之前一直对这块迷迷糊糊.看到了一篇博文写的很好 ...

反卷积(Deconvolution)上采样(Upsampling)上池化(Unpooling)的区别——附翻译

反卷积(Deconvolution)上采样(Upsampling)上池化(Unpooling)的区别——附翻译相关推荐

最新文章

热门文章