Self-supervised GAN: Analysis and Improvement with Multi-class Minimax Game

by   Ngoc-Trung Tran, et al.
Singapore University of Technology and Design

Self-supervised (SS) learning is a powerful approach for representation learning using unlabeled data. Recently, it has been applied to Generative Adversarial Networks (GAN) training. Specifically, SS tasks were proposed to address the catastrophic forgetting issue in the GAN discriminator. In this work, we perform an in-depth analysis to understand how SS tasks interact with learning of generator. From the analysis, we identify issues of SS tasks which allow a severely mode-collapsed generator to excel the SS tasks. To address the issues, we propose new SS tasks based on a multi-class minimax game. The competition between our proposed SS tasks in the game encourages the generator to learn the data distribution and generate diverse samples. We provide both theoretical and empirical analysis to support that our proposed SS tasks have better convergence property. We conduct experiments to incorporate our proposed SS tasks into two different GAN baseline models. Our approach establishes state-of-the-art FID scores on CIFAR-10, CIFAR-100, STL-10, CelebA, Imagenet 32×32 and Stacked-MNIST datasets, outperforming existing works by considerable margins in some cases. Our unconditional GAN model approaches performance of conditional GAN without using labeled data. Our code: <>


page 6

page 18

page 19


Self-supervised GANs with Label Augmentation

Recently, transformation-based self-supervised learning has been applied...

Versatile Auxiliary Classifier with Generative Adversarial Network (VAC+GAN), Multi Class Scenarios

Conditional generators learn the data distribution for each class in a m...

Self-Supervised GAN to Counter Forgetting

GANs involve training two networks in an adversarial game, where each ne...

Teaching a GAN What Not to Learn

Generative adversarial networks (GANs) were originally envisioned as uns...

Dual Discriminator Generative Adversarial Nets

We propose in this paper a novel approach to tackle the problem of mode ...

cGANs with Multi-Hinge Loss

We propose a new algorithm to incorporate class conditional information ...

Few-Features Attack to Fool Machine Learning Models through Mask-Based GAN

GAN is a deep-learning based generative approach to generate contents su...

Please sign up or login with your details

Forgot password? Click here to reset