mlsanityData to 7 Oct 2026

UQGAN: A Unified Model for Uncertainty Quantification of Deep Classifiers trained via Conditional GANs

arXiv 2201.13279 ↗First posted 31 Jan 2022cs.CVcited by 16

Not on the map. Why?

Abstract (arXiv)

We present an approach to quantifying both aleatoric and epistemic uncertainty for deep neural networks in image classification, based on generative adversarial networks (GANs). While most works in the literature that use GANs to generate out-of-distribution (OoD) examples only focus on the evaluation of OoD detection, we present a GAN based approach to learn a classifier that produces proper uncertainties for OoD examples as well as for false positives (FPs). Instead of shielding the entire in-distribution data with GAN generated OoD examples which is state-of-the-art, we shield each class separately with out-of-class examples generated by a conditional GAN and complement this with a one-vs-all image classifier. In our experiments, in particular on CIFAR10, CIFAR100 and Tiny ImageNet, we improve over the OoD detection and FP detection performance of state-of-the-art GAN-training based classifiers. Furthermore, we also find that the generated GAN examples do not significantly affect the calibration error of our classifier and result in a significant gain in model accuracy.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). Builds on 40 of its 83 references that are in the map. First posted on arXiv 31 Jan 2022.

Builds on

40 of 83 references.

References · 40

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  5. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  6. 2017On Calibration of Modern Neural Networkscited by 4,860
  7. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  8. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  9. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  10. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  11. 2017Improved Training of Wasserstein GANscited by 2,223
  12. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
28 more
  1. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
  2. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,325
  3. 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,274
  4. 2018Deep Anomaly Detection with Outlier Exposurecited by 939
  5. 2019Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methodscited by 903
  6. 2018Evidential Deep Learning to Quantify Classification Uncertaintycited by 728
  7. 2021A Survey of Uncertainty in Deep Neural Networkscited by 675
  8. 2017Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discoverycited by 566
  9. 2015Weight Uncertainty in Neural Networkscited by 554
  10. 2019Likelihood Ratios for Out-of-Distribution Detectioncited by 451
  11. 2017Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samplescited by 389
  12. 2018Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problemcited by 323
  13. 2018Learning Confidence for Out-of-Distribution Detection in Neural Networkscited by 245
  14. 2017EMNIST: an extension of MNIST to handwritten letterscited by 212
  15. 2020Pitfalls of In-Domain Uncertainty Estimation and Ensembling in Deep Learningcited by 208
  16. 2015Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inferencecited by 159
  17. 2018Universal approximations of invariant maps by neural networkscited by 127
  18. 2021OVANet: One-vs-All Network for Universal Domain Adaptationcited by 92
  19. 2019PAC Confidence Sets for Deep Neural Networks via Calibrated Predictioncited by 59
  20. 2019Out-of-distribution Detection in Classifiers via Generationcited by 49
  21. 2020Uncertainty-Aware Deep Classifiers using Generative Modelscited by 41
  22. 2020Revisiting One-vs-All Classifiers for Predictive Uncertainty and Out-of-Distribution Detection in Neural Networkscited by 31
  23. 2020Dense open-set recognition with synthetic outliers generated by Real NVPcited by 29
  24. 2018Building robust classifiers through generation of confident out of distribution examplescited by 20
  25. 2020One Versus all for deep Neural Network Incertitude (OVNNI) quantificationcited by 17
  26. 2019Open Set Recognition Through Deep Neural Network Uncertainty: Does Out-of-Distribution Detection Require Generative Classifiers?cited by 13
  27. 2019Analysis of Confident-Classifiers for Out-of-distribution Detectioncited by 7
  28. 2019Enhancing the Robustness of Deep Neural Networks by Boundary Conditional GANcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 5; 2024: 4; 2025: 4; 2026: 3.

16 papers.

Sort:

By area:

  1. 2023A Survey on Uncertainty Quantification Methods for Deep Learningcited by 78
  2. 2023Ten Years of Generative Adversarial Nets (GANs): A survey of the state-of-the-artcited by 14
  3. 2023Using AI Uncertainty Quantification to Improve Human Decision-Makingcited by 11
  4. 2025Uncertainty Quantification for Machine Learning in Healthcare: A Surveycited by 11
  5. 2025CLEAR: Calibrated Learning for Epistemic and Aleatoric Riskcited by 6
  6. 2024How Deep is your Guess? A Fresh Perspective on Deep Learning for Medical Time-Series Imputationcited by 5
  7. 2024On the Potential of Open-Vocabulary Models for Object Detection in Unusual Street Scenescited by 5
  8. 2024Hierarchical Visual Categories Modeling: A Joint Representation Learning and Density Estimation Framework for Out-of-Distribution Detectioncited by 4
  9. 2026Epistemic Generative Adversarial Networkscited by 4
  10. 2025Generative AI for Autonomous Driving: A Reviewcited by 3
  11. 2026Quantifying Epistemic Uncertainty in Diffusion Modelscited by 2
  12. 2023Uncertainty quantification for deep learning-based schemes for solving high-dimensional backward stochastic differential equationscited by 1
4 more
  1. 2023Uncertainty Quantification of Deep Learning for Spatiotemporal Data: Challenges and Opportunitiescited by 1
  2. 2024Explaining an image classifier with a generative model conditioned by uncertaintycited by 1
  3. 2025Multidimensional Distributional Neural Network Output Demonstrated in Super-Resolution of Surface Wind Speedcited by 1
  4. 2026Out-of-Distribution Object Detection in Street Scenes via Synthetic Outlier Exposure and Transfer Learningcited by 0