DeshuffleGAN: A Self-Supervised GAN to Improve Structure Learning

06/15/2020
by   Gulcin Baykal, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 4

research
11/03/2020

Exploring DeshuffleGANs in Self-Supervised Generative Adversarial Networks

Generative Adversarial Networks (GANs) have become the most used network...
research
10/19/2020

LT-GAN: Self-Supervised GAN with Latent Transformation Detection

Generative Adversarial Networks (GANs) coupled with self-supervised task...
research
09/02/2021

FA-GAN: Feature-Aware GAN for Text to Image Synthesis

Text-to-image synthesis aims to generate a photo-realistic image from a ...
research
01/29/2019

PA-GAN: Improving GAN Training by Progressive Augmentation

Training of Generative Adversarial Networks (GANs) is notoriously fragil...
research
09/01/2017

PassGAN: A Deep Learning Approach for Password Guessing

State-of-the-art password guessing tools, such as HashCat and John the R...
research
08/06/2020

GL-GAN: Adaptive Global and Local Bilevel Optimization model of Image Generation

Although Generative Adversarial Networks have shown remarkable performan...
research
01/20/2023

Spatial Steerability of GANs via Self-Supervision from Discriminator

Generative models make huge progress to the photorealistic image synthes...

Please sign up or login with your details

Forgot password? Click here to reset