mlsanityData to 7 Oct 2026

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

arXiv 1803.01541 ↗First posted 5 Mar 2018cs.CV cs.LG stat.MLcited by 49

Not on the map. Why?

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.

Key facts. Cited by 49 papers in the map (data through 7 Oct 2026). First posted on arXiv 5 Mar 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 19; 2022: 14; 2023: 3; 2024: 5; 2025: 7; 2026: 1.

49 papers.

Sort:

By area:

  1. 2021A Survey on Deep Semi-supervised Learningcited by 250
  2. 2021Beyond Self-attention: External Attention using Two Linear Layers for Visual Taskscited by 109
  3. 2021Prior and Posterior Networks: A Survey on Evidential Deep Learning Methods For Uncertainty Estimationcited by 71
  4. 2021Consistency Regularization for Variational Auto-Encoderscited by 50
  5. 2021Training GANs with Stronger Augmentations via Contrastive Discriminatorcited by 45
  6. 2021An error analysis of generative adversarial networks for learning distributionscited by 35
  7. 2021Gradient Normalization for Generative Adversarial Networkscited by 25
  8. 2021Deepfake Detection Scheme Based on Vision Transformer and Distillationcited by 22
  9. 2022MutexMatch: Semi-Supervised Learning with Mutex-Based Consistency Regularizationcited by 22
  10. 2022Kantorovich Strikes Back! Wasserstein GANs are not Optimal Transport?cited by 19
  11. 2021Manifold Learning Benefits GANscited by 14
  12. 2021Adaptive Boosting for Domain Adaptation: Towards Robust Predictions in Scene Segmentationcited by 13
37 more
  1. 2023Few shot font generation via transferring similarity guided global style and quantization local stylecited by 8
  2. 2021Understanding Entropic Regularization in GANscited by 6
  3. 2021Generative Convolution Layer for Image Generationcited by 5
  4. 2021A Novel Generator with Auxiliary Branch for Improving GAN Performancecited by 4
  5. 2023Fair Text Classification with Wasserstein Independencecited by 4
  6. 2023Generator Born from Classifiercited by 4
  7. 2021Training Wasserstein GANs without gradient penaltiescited by 3
  8. 2022Unveiling the Latent Space Geometry of Push-Forward Generative Modelscited by 3
  9. 2024A Wasserstein perspective of Vanilla GANscited by 3
  10. 2025Fair Text Classification via Transferable Representationscited by 3
  11. 2025Text-to-3D Generation using Jensen-Shannon Score Distillationcited by 2
  12. 2021Semi-Supervised Learning using Siamese Networkscited by 1
  13. 2021Rethinking Multidimensional Discriminator Output for Generative Adversarial Networkscited by 1
  14. 2021GraN-GAN: Piecewise Gradient Normalization for Generative Adversarial Networkscited by 1
  15. 2022Karaoker: Alignment-free singing voice synthesis with speech training datacited by 1
  16. 2022HessianFR: An Efficient Hessian-based Follow-the-Ridge Algorithm for Minimax Optimizationcited by 1
  17. 2022Learning Distributions by Generative Adversarial Networks: Approximation and Generalizationcited by 1
  18. 2022Mining Multi-Label Samples from Single Positive Labelscited by 1
  19. 2022On Deep Learning in Password Guessing, a Surveycited by 1
  20. 2022DVGAN: Stabilize Wasserstein GAN training for time-domain Gravitational Wave physicscited by 1
  21. 2022Analysing the effectiveness of a generative model for semi-supervised medical image segmentationcited by 1
  22. 2024VFLGAN: Vertical Federated Learning-based Generative Adversarial Network for Vertically Partitioned Data Publicationcited by 1
  23. 2024Rethinking Image Skip Connections in StyleGAN2cited by 1
  24. 2025Displacement-Sparse Neural Optimal Transportcited by 1
  25. 2025Efficiency without Compromise: CLIP-aided Text-to-Image GANs with Increased Diversitycited by 1
  26. 2021Transfer of Pretrained Model Weights Substantially Improves Semi-Supervised Image Classificationcited by 0
  27. 2021LR-to-HR Face Hallucination with an Adversarial Progressive Attribute-Induced Networkcited by 0
  28. 2022Effective Shortcut Technique for GANcited by 0
  29. 2022Signature and Log-signature for the Study of Empirical Distributions Generated with GANscited by 0
  30. 2022Improving GANs with a Feature Cycling Generatorcited by 0
  31. 2022Gradient Imitation Reinforcement Learning for General Low-Resource Information Extractioncited by 0
  32. 2024cDVGAN: One Flexible Model for Multi-class Gravitational Wave Signal and Glitch Generationcited by 0
  33. 2024Object Tracking in a 360o View: A Novel Perspective on Bridging the Gap to Biomedical Advancementscited by 0
  34. 2025Distributed Gossip-GAN for Low-overhead CSI Feedback Training in FDD mMIMO-OFDM Systemscited by 0
  35. 2025Taming Generative Synthetic Data for X-ray Prohibited Item Detectioncited by 0
  36. 2025Generative Model-Aided Continual Learning for CSI Feedback in FDD mMIMO-OFDM Systemscited by 0
  37. 2026Neural solver for Wasserstein Geodesics and optimal transport dynamicscited by 0