DeshuffleGAN: A Self-Supervised GAN to Improve Structure Learning

TL;DR

DeshuffleGAN introduces a self-supervised deshuffling task to enhance GANs' ability to learn spatial structures, leading to more realistic image generation across multiple datasets.

Contribution

The paper proposes DeshuffleGAN, a novel self-supervised approach that improves GAN structure learning by incorporating a deshuffling task for better spatial understanding.

Findings

Improved realism in generated images.

Consistent performance gains over baseline methods.

Effective across multiple datasets.

Abstract

Generative Adversarial Networks (GANs) triggered an increased interest in problem of image generation due to their improved output image quality and versatility for expansion towards new methods. Numerous GAN-based works attempt to improve generation by architectural and loss-based extensions. We argue that one of the crucial points to improve the GAN performance in terms of realism and similarity to the original data distribution is to be able to provide the model with a capability to learn the spatial structure in data. To that end, we propose the DeshuffleGAN to enhance the learning of the discriminator and the generator, via a self-supervision approach. Specifically, we introduce a deshuffling task that solves a puzzle of randomly shuffled image tiles, which in turn helps the DeshuffleGAN learn to increase its expressive capacity for spatial structure and realistic appearance. We provide experimental evidence for the performance improvement in generated images, compared to the baseline methods, which is consistently observed over two different datasets.