Improving the Improved Training of Wasserstein GANs: A Consistency Term and Its Dual Effect

03/05/2018
by   Xiang Wei, et al.
0

Despite being impactful on a variety of problems and applications, the generative adversarial nets (GANs) are remarkably difficult to train. This issue is formally analyzed by arjovsky2017towards, who also propose an alternative direction to avoid the caveats in the minmax two-player training of GANs. The corresponding algorithm, called Wasserstein GAN (WGAN), hinges on the 1-Lipschitz continuity of the discriminator. In this paper, we propose a novel approach to enforcing the Lipschitz continuity in the training procedure of WGANs. Our approach seamlessly connects WGAN with one of the recent semi-supervised learning methods. As a result, it gives rise to not only better photo-realistic samples than the previous methods but also state-of-the-art semi-supervised learning results. In particular, our approach gives rise to the inception score of more than 5.0 with only 1,000 CIFAR-10 images and is the first that exceeds the accuracy of 90 labeled images, to the best of our knowledge.

READ FULL TEXT

page 6

page 7

page 8

page 15

page 16

page 17

research
07/12/2019

Virtual Adversarial Lipschitz Regularization

Generative adversarial networks (GANs) are one of the most popular appro...
research
12/07/2017

Semi-Supervised Learning with IPM-based GANs: an Empirical Study

We present an empirical investigation of a recent class of Generative Ad...
research
02/13/2021

Multi-class Generative Adversarial Nets for Semi-supervised Image Classification

From generating never-before-seen images to domain adaptation, applicati...
research
05/24/2017

Semi-supervised Learning with GANs: Manifold Invariance with Improved Inference

Semi-supervised learning methods using Generative Adversarial Networks (...
research
03/21/2023

Linking generative semi-supervised learning and generative open-set recognition

This study investigates the relationship between semi-supervised learnin...
research
04/06/2021

Generalization of GANs under Lipschitz continuity and data augmentation

Generative adversarial networks (GANs) have been being widely used in va...
research
05/23/2018

Semi-Supervised Learning with GANs: Revisiting Manifold Regularization

GANS are powerful generative models that are able to model the manifold ...

Please sign up or login with your details

Forgot password? Click here to reset