Checkerboard artifact free sub-pixel convolution: A note on sub-pixel convolution, resize convolution and convolution resize

07/10/2017 ∙ by Andrew Aitken, et al. ∙ 0

The most prominent problem associated with the deconvolution layer is the presence of checkerboard artifacts in output images and dense labels. To combat this problem, smoothness constraints, post processing and different architecture designs have been proposed. Odena et al. highlight three sources of checkerboard artifacts: deconvolution overlap, random initialization and loss functions. In this note, we proposed an initialization method for sub-pixel convolution known as convolution NN resize. Compared to sub-pixel convolution initialized with schemes designed for standard convolution kernels, it is free from checkerboard artifacts immediately after initialization. Compared to resize convolution, at the same computational complexity, it has more modelling power and converges to solutions with smaller test errors.



There are no comments yet.


page 9

page 10

page 11

page 12

page 13

page 14

page 15

page 16

Code Repositories


Convolution NN resize initialization for subpixel convolutions

view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.