It is a 1x1 convolution kernel. This helps in acquiring pixel by pixel level feature extraction. But the main purpose is,
A kernel with spaces in between each cell is called dilation. 1-Dilated kernel has 1 cell spaces around pixels. 1-Dilated kernels have the capacity to extract higher spatial information from an effective receptive field. Dilated kernels can be used along with regular kernels. Since, a 0-Dilated kernel is a regular kernel .
Dilated convolution are used for applications like semantic segmentation with one label per pixel , image super resolution , denoising etc.
This paper infers that the architecture assumes the fact that dilated convolution increases the receptive field exponentially through the network.
From the paper Deconvolution Networks
Written on October 17th, 2018 by karthik
Convolutional networks are a bottom-up approach where the input signal is subjected to multiple layers of convolutions, non-linearities and sub-sampling. By contrast, each layer in our Deconvolutional Network is top-down; it seeks to generate the input signal by a sum over convolutions of the feature maps (as opposed to the input) with learned filters.