如何理解deconvolution?
来源:互联网 发布:windows脚本编程 编辑:程序博客网 时间:2024/06/06 17:08
链接:https://www.zhihu.com/question/43609045/answer/132235276
来源:知乎
著作权归作者所有。商业转载请联系作者获得授权,非商业转载请注明出处。
Deconvolution大致可以分为以下几个方面:
(1)unsupervised learning,其实就是covolutional sparse coding[1][2]:这里的deconv只是观念上和传统的conv反向,传统的conv是从图片生成feature map,而deconv是用unsupervised的方法找到一组kernel和feature map,让它们重建图片。
(2)CNN可视化[3]:通过deconv将CNN中conv得到的feature map还原到像素空间,以观察特定的feature map对哪些pattern的图片敏感,这里的deconv其实不是conv的可逆运算,只是conv的transpose,所以tensorflow里一般取名叫transpose_conv。
(3)upsampling[4][5]:在pixel-wise prediction比如image segmentation[4]以及image generation[5]中,由于需要做原始图片尺寸空间的预测,而卷积由于stride往往会降低图片size, 所以往往需要通过upsampling的方法来还原到原始图片尺寸,deconv就充当了一个upsampling的角色
[1] Zeiler M D, Krishnan D, Taylor G W, et al. Deconvolutional networks[C]. Computer Vision and Pattern Recognition, 2010.
[2] Zeiler M D, Taylor G W, Fergus R, et al. Adaptive deconvolutional networks for mid and high level feature learning[C]. International Conference on Computer Vision, 2011.
[3] Zeiler M D, Fergus R. Visualizing and Understanding Convolutional Networks[C]. European Conference on Computer Vision, 2013.
[4] Long J, Shelhamer E, Darrell T, et al. Fully convolutional networks for semantic segmentation[C]. Computer Vision and Pattern Recognition, 2015.
[5] Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
[8] Convolution arithmetic tutorial
- 如何理解deconvolution?
- Deconvolution Network简单理解)
- Deconvolution Network简单理解
- Deconvolution
- Deconvolution
- Deep learning:五十(Deconvolution Network简单理解)
- 理解深度学习中的deconvolution networks
- caffe 里deconvolution layer (解卷积层)的理解
- Richardson–Lucy deconvolution
- blind deconvolution parameter tuning
- Deconvolution Using Theano
- Deconvolution/Transposed convolution
- Convolution Networks 和Deconvolution Networks
- Convolution Networks 和Deconvolution Networks
- Convolution Networks 和Deconvolution Networks
- 2D Deconvolution for Image Reconstruction
- 2D Deconvolution for Image Reconstruction
- Learning Deconvolution Network for Semantic Segmentation
- iOS自动化打包
- 难缠的code——java中关于分割字符串的几个坑
- Professional JS 7.2.1闭包与变量----8.1.4窗口大小
- js 继承
- 先序遍历、中序遍历、后序遍历(二叉树)
- 如何理解deconvolution?
- 能量项链 NOIP2006 Codevs1154
- 程序员面试金典:高度最小的BST、输出单层结点
- OpenVR——驱动接口之IClientTrackedDeviceProvider简介
- Meteor Shower POJ
- 得到三个[10-100)的随机数,按降序排列。注意:只能用if语句
- 【Linux】文件和目录属性及其修改——chgrp、chown、chmod、touch...
- LinkedList简介
- Logo图标的含义