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

arXiv: https://arxiv.org/abs/1803.01541 · HTML: https://mlsanity.com/paper/1803.01541/

## Key facts

- Cited by 49 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Mar 2018.

## Built on by (most cited first, 30 of 49)

- [A Survey on Deep Semi-supervised Learning](https://mlsanity.com/paper/2103.00550/) (2021)
- [Beyond Self-attention: External Attention using Two Linear Layers for Visual Tasks](https://mlsanity.com/paper/2105.02358/) (2021)
- [Prior and Posterior Networks: A Survey on Evidential Deep Learning Methods For Uncertainty Estimation](https://mlsanity.com/paper/2110.03051/) (2021)
- [Consistency Regularization for Variational Auto-Encoders](https://mlsanity.com/paper/2105.14859/) (2021)
- [Training GANs with Stronger Augmentations via Contrastive Discriminator](https://mlsanity.com/paper/2103.09742/) (2021)
- [An error analysis of generative adversarial networks for learning distributions](https://mlsanity.com/paper/2105.13010/) (2021)
- [Gradient Normalization for Generative Adversarial Networks](https://mlsanity.com/paper/2109.02235/) (2021)
- [Deepfake Detection Scheme Based on Vision Transformer and Distillation](https://mlsanity.com/paper/2104.01353/) (2021)
- [MutexMatch: Semi-Supervised Learning with Mutex-Based Consistency Regularization](https://mlsanity.com/paper/2203.14316/) (2022)
- [Kantorovich Strikes Back! Wasserstein GANs are not Optimal Transport?](https://mlsanity.com/paper/2206.07767/) (2022)
- [Manifold Learning Benefits GANs](https://mlsanity.com/paper/2112.12618/) (2021)
- [Adaptive Boosting for Domain Adaptation: Towards Robust Predictions in Scene Segmentation](https://mlsanity.com/paper/2103.15685/) (2021)
- [Few shot font generation via transferring similarity guided global style and quantization local style](https://mlsanity.com/paper/2309.00827/) (2023)
- [Understanding Entropic Regularization in GANs](https://mlsanity.com/paper/2111.01387/) (2021)
- [Generative Convolution Layer for Image Generation](https://mlsanity.com/paper/2111.15171/) (2021)
- [A Novel Generator with Auxiliary Branch for Improving GAN Performance](https://mlsanity.com/paper/2112.14968/) (2021)
- [Fair Text Classification with Wasserstein Independence](https://mlsanity.com/paper/2311.12689/) (2023)
- [Generator Born from Classifier](https://mlsanity.com/paper/2312.02470/) (2023)
- [Training Wasserstein GANs without gradient penalties](https://mlsanity.com/paper/2110.14150/) (2021)
- [Unveiling the Latent Space Geometry of Push-Forward Generative Models](https://mlsanity.com/paper/2207.10541/) (2022)
- [A Wasserstein perspective of Vanilla GANs](https://mlsanity.com/paper/2403.15312/) (2024)
- [Fair Text Classification via Transferable Representations](https://mlsanity.com/paper/2503.07691/) (2025)
- [Text-to-3D Generation using Jensen-Shannon Score Distillation](https://mlsanity.com/paper/2503.10660/) (2025)
- [Semi-Supervised Learning using Siamese Networks](https://mlsanity.com/paper/2109.00794/) (2021)
- [Rethinking Multidimensional Discriminator Output for Generative Adversarial Networks](https://mlsanity.com/paper/2109.03378/) (2021)
- [GraN-GAN: Piecewise Gradient Normalization for Generative Adversarial Networks](https://mlsanity.com/paper/2111.03162/) (2021)
- [Karaoker: Alignment-free singing voice synthesis with speech training data](https://mlsanity.com/paper/2204.04127/) (2022)
- [HessianFR: An Efficient Hessian-based Follow-the-Ridge Algorithm for Minimax Optimization](https://mlsanity.com/paper/2205.11030/) (2022)
- [Learning Distributions by Generative Adversarial Networks: Approximation and Generalization](https://mlsanity.com/paper/2205.12601/) (2022)
- [Mining Multi-Label Samples from Single Positive Labels](https://mlsanity.com/paper/2206.05764/) (2022)

## Abstract (arXiv)

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 citearjovsky2017towards, 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% on the CIFAR-10 dataset using only 4,000 labeled images, to the best of our knowledge.