TransWikia.com

Checkerboard artefacts vs distinct objects in GANs

Data Science Asked on August 25, 2021

I found a very good solution for getting rid of checkerboard artefacts in GANs:

https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix/issues/190

Instead of using Transposed Convolution, use bilinear upsampling

                      nn.Upsample(scale_factor = 2, mode='bilinear'),
                      nn.ReflectionPad2d(1),
                      nn.Conv2d(ngf * mult, int(ngf * mult / 2),
                                         kernel_size=3, stride=1, padding=0),

I replaced padding=0 with padding=1 to keep the same size of the image. The tradeoff, though, is that the Generator doesn’t learn to evolve distinct objects as with Transposed Convolution. For example, on Street View House Number (SVHN) dataset, the one on the left was made with Transposed Convolution, the one on the right with Upsampling:

enter image description here
enter image description here

I haven’t found any good explanations on the difference in results so far.

Add your own answers!

Ask a Question

Get help from others!

© 2024 TransWikia.com. All rights reserved. Sites we Love: PCI Database, UKBizDB, Menu Kuliner, Sharing RPP