mlsanityData to 14 Oct 2026

Epistemic Generative Adversarial Networks

arXiv 2603.18348 ↗First posted 18 Mar 2026cs.LG cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Generative models, particularly Generative Adversarial Networks (GANs), often suffer from a lack of output diversity, frequently generating similar samples rather than a wide range of variations. This paper introduces a novel generalization of the GAN loss function based on Dempster-Shafer theory of evidence, applied to both the generator and discriminator. Additionally, we propose an architectural enhancement to the generator that enables it to predict a mass function for each image pixel. This modification allows the model to quantify uncertainty in its outputs and leverage this uncertainty to produce more diverse and representative generations. Experimental evidence shows that our approach not only improves generation variability but also provides a principled framework for modeling and interpreting uncertainty in generative processes.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 29 of its 63 references that are in the map. First posted on arXiv 18 Mar 2026.

Builds on

29 of 63 references.

References · 29

  1. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,527
  2. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  3. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  4. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,626
  5. 2020Training Generative Adversarial Networks with Limited Datacited by 1,186
  6. 2016Least Squares Generative Adversarial Networkscited by 1,001
  7. 2016InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Netscited by 860
  8. 2022The Vendi Score: A Diversity Evaluation Metric for Machine Learningcited by 311
  9. 2017Data Augmentation Generative Adversarial Networkscited by 278
  10. 2017Geometric GANcited by 233
  11. 2016Generative Multi-Adversarial Networkscited by 60
  12. 2017Multi-Agent Diverse Generative Adversarial Networkscited by 59
17 more
  1. 2018DP-GAN: Diversity-Promoting Generative Adversarial Network for Generating Informative and Diversified Textcited by 40
  2. 2023Learn to Accumulate Evidence from All Training Samples: Theory and Practicecited by 29
  3. 2024Diffusion Model Guided Sampling with Pixel-Wise Aleatoric Uncertainty Estimationcited by 20
  4. 2023Random-Set Neural Networks (RS-NN)cited by 19
  5. 2022UQGAN: A Unified Model for Uncertainty Quantification of Deep Classifiers trained via Conditional GANscited by 16
  6. 2022Epistemic Deep Learningcited by 15
  7. 2018Visions of a generalized probability theorycited by 13
  8. 2022Selectively increasing the diversity of GAN-generated samplescited by 9
  9. 2025Epistemic Artificial Intelligence is Essential for Machine Learning Models to Truly 'Know When They Do Not Know'cited by 8
  10. 2023Reasoning with random sets: An agenda for the futurecited by 6
  11. 2025Epistemic Wrapping for Uncertainty Quantificationcited by 5
  12. 2025Uncertainty-Aware Autonomous Vehicles: Predicting the Road Aheadcited by 5
  13. 2023A Belief Model for Conflicting and Uncertain Evidence -- Connecting Dempster-Shafer Theory and the Topology of Evidencecited by 2
  14. 2024VAE-QWGAN: Addressing Mode Collapse in Quantum GANs via Autoencoding Priorscited by 2
  15. 2023Analyzing Effects of Fake Training Data on the Performance of Deep Learning Systemscited by 1
  16. 2023Adaptive Input-image Normalization for Solving the Mode Collapse Problem in GAN-based X-ray Imagescited by 1
  17. 2025FNBT: Full Negation Belief Transformation for Open-World Information Fusion Based on Dempster-Shafer Theory of Evidencecited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026Random-Set Graph Neural Networkscited by 3
  2. 2026Credal Large Language Models for Semantic Commitment under Uncertaintycited by 2
  3. 2026A formal definition and meta-model for a machine theory of mindcited by 1
  4. 2026XU-RS: Explaining Credal Width in Random-Set Language Modelscited by 0