mlsanityData to 7 Oct 2026

Prb-GAN: A Probabilistic Framework for GAN Modelling

arXiv 2107.05241 ↗First posted 12 Jul 2021cs.LG cs.CV stat.MLcited by 0

Not on the map. Why?

Abstract (arXiv)

Generative adversarial networks (GANs) are very popular to generate realistic images, but they often suffer from the training instability issues and the phenomenon of mode loss. In order to attain greater diversity in GAN synthesized data, it is critical to solving the problem of mode loss. Our work explores probabilistic approaches to GAN modelling that could allow us to tackle these issues. We present Prb-GANs, a new variation that uses dropout to create a distribution over the network parameters with the posterior learnt using variational inference. We describe theoretically and validate experimentally using simple and complex datasets the benefits of such an approach. We look into further improvements using the concept of uncertainty measures. Through a set of further modifications to the loss functions for each network of the GAN, we are able to get results that show the improvement of GAN performance. Our methods are extremely simple and require very little modification to existing GAN architecture.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 37 of its 48 references that are in the map. First posted on arXiv 12 Jul 2021.

Builds on

37 of 48 references.

References · 37

  1. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  2. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  3. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  4. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  5. 2017Improved Training of Wasserstein GANscited by 2,223
  6. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,618
  7. 2017Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semanticscited by 1,345
  8. 2017StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translationcited by 1,036
  9. 2016Least Squares Generative Adversarial Networkscited by 1,000
  10. 2019AugMix: A Simple Data Processing Method to Improve Robustness and Uncertaintycited by 897
  11. 2016f-GAN: Training Generative Neural Samplers using Variational Divergence Minimizationcited by 504
  12. 2019SinGAN: Learning a Generative Model from a Single Natural Imagecited by 348
25 more
  1. 2017Are GANs Created Equal? A Large-Scale Studycited by 267
  2. 2019Large Scale Adversarial Representation Learningcited by 238
  3. 2018A Note on the Inception Scorecited by 225
  4. 2018Generative Adversarial Networks for Extreme Learned Image Compressioncited by 213
  5. 2019Mode Seeking Generative Adversarial Networks for Diverse Image Synthesiscited by 138
  6. 2016Mode Regularized Generative Adversarial Networkscited by 123
  7. 2019Max-Sliced Wasserstein Distance and its use for GANscited by 118
  8. 2018Generative Modeling using the Sliced Wasserstein Distancecited by 108
  9. 2019AutoGAN: Neural Architecture Search for Generative Adversarial Networkscited by 94
  10. 2018Generative Dual Adversarial Network for Generalized Zero-shot Learningcited by 61
  11. 2019Sliced Wasserstein Generative Modelscited by 61
  12. 2016Generative Multi-Adversarial Networkscited by 60
  13. 2017Multi-Agent Diverse Generative Adversarial Networkscited by 59
  14. 2019Attending to Discriminative Certainty for Domain Adaptationcited by 37
  15. 2017Bayesian GANcited by 31
  16. 2017Loss-Sensitive Generative Adversarial Networks on Lipschitz Densitiescited by 29
  17. 2017Boundary-Seeking Generative Adversarial Networkscited by 27
  18. 2019On Stabilizing Generative Adversarial Training with Noisecited by 25
  19. 2018Dropout-GAN: Learning from a Dynamic Ensemble of Discriminatorscited by 15
  20. 2019Looking back at Labels: A Class based Domain Adaptation Techniquecited by 11
  21. 2018Mixture Density Generative Adversarial Networkscited by 9
  22. 2019Robust Conditional GAN from Uncertainty-Aware Pairwise Comparisonscited by 9
  23. 2019Curriculum based Dropout Discriminator for Domain Adaptationcited by 6
  24. 2019GAN-Tree: An Incrementally Learned Hierarchical Generative Framework for Multi-Modal Data Distributionscited by 5
  25. 2017Probabilistic Generative Adversarial Networkscited by 1

Built on by

Not cited yet.