Dilated Convolution [explained]

Dilated convolution, also known as Atrous Convolution or convolution with holes, first came into light by the paper "Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs". The idea behind dilated convolution is to "inflate" the kernel which in turn skips some of the points. We can see the difference in the general formula and some visualization.

Table of content:

Introduction to Dilated ConvolutionDilated convolution in TensorflowDilated convolution in actionDila...