mlsanityData to 7 Oct 2026

Uncertainty Estimation Using a Single Deep Deterministic Neural Network

arXiv 2003.02037 ↗First posted 4 Mar 2020cs.LG stat.MLcited by 37

Not on the map. Why?

Abstract (arXiv)

We propose a method for training a deterministic deep model that can find and reject out of distribution data points at test time with a single forward pass. Our approach, deterministic uncertainty quantification (DUQ), builds upon ideas of RBF networks. We scale training in these with a novel loss function and centroid updating scheme and match the accuracy of softmax models. By enforcing detectability of changes in the input using a gradient penalty, we are able to reliably detect out of distribution data. Our uncertainty quantification scales well to large datasets, and using a single model, we improve upon or match Deep Ensembles in out of distribution detection on notable difficult dataset pairs such as FashionMNIST vs. MNIST, and CIFAR-10 vs. SVHN.

Key facts. Cited by 37 papers in the map (data through 7 Oct 2026). First posted on arXiv 4 Mar 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 14; 2022: 8; 2023: 5; 2024: 8; 2025: 1; 2026: 1.

37 papers.

Sort:

  1. 2021SegmentMeIfYouCan: A Benchmark for Anomaly Segmentationcited by 150
  2. 2021DEUP: Direct Epistemic Uncertainty Predictioncited by 102
  3. 2021The Promises and Pitfalls of Deep Kernel Learningcited by 81
  4. 2021Understanding Softmax Confidence and Uncertaintycited by 62
  5. 2021Generating Interpretable Counterfactual Explanations By Implicit Minimisation of Epistemic and Aleatoric Uncertaintiescited by 41
  6. 2022Post-hoc Uncertainty Learning using a Dirichlet Meta-Modelcited by 31
  7. 2021Corner Cases for Visual Perception in Automated Driving: Some Guidance on Detection Approachescited by 27
  8. 2023Uncertainty-based Fairness Measurescited by 15
  9. 2024Interpreting Predictive Probabilities: Model Confidence or Human Label Variation?cited by 15
  10. 2022Towards OOD Detection in Graph Classification from Uncertainty Estimation Perspectivecited by 13
  11. 2021The Peril of Popular Deep Learning Uncertainty Estimation Methodscited by 11
  12. 2021Uncertainty-Aware Credit Card Fraud Detection Using Deep Learningcited by 10
25 more
  1. 2022Semi-supervised Deep Learning for Image Classification with Distribution Mismatch: A Surveycited by 8
  2. 2024Function Space Diversity for Uncertainty Prediction via Repulsive Last-Layer Ensemblescited by 8
  3. 2024Provable Uncertainty Decomposition via Higher-Order Calibrationcited by 8
  4. 2024Advancing Deep Active Learning & Data Subset Selection: Unifying Principles with Information-Theory Intuitionscited by 7
  5. 2025OCCUQ: Exploring Efficient Uncertainty Quantification for 3D Occupancy Predictioncited by 6
  6. 2021Confidence Aware Neural Networks for Skin Cancer Detectioncited by 5
  7. 2021Distributional Gaussian Process Layers for Outlier Detection in Image Segmentationcited by 4
  8. 2021Towards Robust Active Feature Acquisitioncited by 4
  9. 2022Invariant Representation Driven Neural Classifier for Anti-QCD Jet Taggingcited by 4
  10. 2022Improving Generalization via Uncertainty Driven Perturbationscited by 3
  11. 2021Dealing with Distribution Mismatch in Semi-supervised Deep Learning for Covid-19 Detection Using Chest X-ray Images: A Novel Approach Using Feature Densitiescited by 2
  12. 2022Distinction Maximization Loss: Efficiently Improving Out-of-Distribution Detection and Uncertainty Estimation by Replacing the Loss and Calibratingcited by 2
  13. 2023Generalized Uncertainty of Deep Neural Networks: Taxonomy and Applicationscited by 2
  14. 2023Implicit regularisation in stochastic gradient descent: from single-objective to two-player gamescited by 2
  15. 2021Automatic quality control framework for more reliable integration of machine learning-based image segmentation into medical workflowscited by 1
  16. 2022Distributional Gaussian Processes Layers for Out-of-Distribution Detectioncited by 1
  17. 2023Detecting and Learning Out-of-Distribution Data in the Open world: Algorithm and Theorycited by 1
  18. 2024Masked Gamma-SSL: Learning Uncertainty Estimation via Masked Image Modelingcited by 1
  19. 2024Mitigating Distributional Shift in Semantic Segmentation via Uncertainty Estimation from Unlabelled Datacited by 1
  20. 2024Uncertainties of Latent Representations in Computer Visioncited by 1
  21. 2021Advances in Electron Microscopy with Deep Learningcited by 0
  22. 2022Improving Semi-supervised Deep Learning by using Automatic Thresholding to Deal with Out of Distribution Data for COVID-19 Detection using Chest X-ray Imagescited by 0
  23. 2023eXplainable Artificial Intelligence on Medical Images: A Surveycited by 0
  24. 2024Neural Network Meta Classifier: Improving the Reliability of Anomaly Segmentationcited by 0
  25. 2026Softmax is not Enough (for Adaptive Conformal Classification)cited by 0