mlsanityData to 7 Oct 2026

On the Practicality of Deterministic Epistemic Uncertainty

arXiv 2107.00649 ↗First posted 1 Jul 2021cs.CVcited by 62

Not on the map. Why?

Abstract (arXiv)

A set of novel approaches for estimating epistemic uncertainty in deep neural networks with a single forward pass has recently emerged as a valid alternative to Bayesian Neural Networks. On the premise of informative representations, these deterministic uncertainty methods (DUMs) achieve strong performance on detecting out-of-distribution (OOD) data while adding negligible computational costs at inference time. However, it remains unclear whether DUMs are well calibrated and can seamlessly scale to real-world applications - both prerequisites for their practical deployment. To this end, we first provide a taxonomy of DUMs, and evaluate their calibration under continuous distributional shifts. Then, we extend them to semantic segmentation. We find that, while DUMs scale to realistic vision tasks and perform well on OOD detection, the practicality of current methods is undermined by poor calibration under distributional shifts.

Key facts. Cited by 62 papers in the map (data through 7 Oct 2026). Builds on 56 of its 88 references that are in the map. First posted on arXiv 1 Jul 2021.

Builds on

56 of 88 references.

References · 56

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  3. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  4. 2013Intriguing properties of neural networkscited by 5,114
  5. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  6. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  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. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  10. 2017CARLA: An Open Urban Driving Simulatorcited by 2,431
  11. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  12. 2017Improved Training of Wasserstein GANscited by 2,223
38 more
  1. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,618
  2. 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,274
  3. 2015Multi-Scale Context Aggregation by Dilated Convolutionscited by 1,128
  4. 2017Deep Bayesian Active Learning with Image Datacited by 812
  5. 2013Domain Generalization via Invariant Feature Representationcited by 622
  6. 2015Variational Dropout and the Local Reparameterization Trickcited by 489
  7. 2018Do Deep Generative Models Know What They Don't Know?cited by 443
  8. 2017Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samplescited by 389
  9. 2020Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awarenesscited by 389
  10. 2020BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learningcited by 368
  11. 2018Invertible Residual Networkscited by 364
  12. 2019Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Comingcited by 332
  13. 2017Dilated Residual Networkscited by 293
  14. 2018Analyzing Inverse Problems with Invertible Neural Networkscited by 239
  15. 2014Scalable Variational Gaussian Process Classificationcited by 226
  16. 2020Contrastive Training for Improved Out-of-Distribution Detectioncited by 186
  17. 2019Evaluating Scalable Bayesian Deep Learning Methods for Robust Computer Visioncited by 182
  18. 2020Training independent subnetworks for robust predictioncited by 177
  19. 2020Efficient and Scalable Bayesian Neural Nets with Rank-1 Factorscited by 171
  20. 2020Posterior Network: Uncertainty Estimation without OOD Samples via Density-Based Pseudo-Countscited by 163
  21. 2018i-RevNet: Deep Invertible Networkscited by 137
  22. 2021Testing for Outliers with Conformal p-valuescited by 133
  23. 2019The Fishyscapes Benchmark: Measuring Blind Spots in Semantic Segmentationcited by 122
  24. 2019A General Framework for Uncertainty Estimation in Deep Learningcited by 119
  25. 2021DEUP: Direct Epistemic Uncertainty Predictioncited by 102
  26. 2016Learning in an Uncertain World: Representing Ambiguity Through Multiple Hypothesescited by 96
  27. 2017Noisy Natural Gradient as Variational Inferencecited by 94
  28. 2019Sampling-free Epistemic Uncertainty Estimation Using Approximated Variance Propagationcited by 74
  29. 2018Bayesian Uncertainty Estimation for Batch Normalized Deep Networkscited by 70
  30. 2019Rates of Convergence for Sparse Variational Gaussian Process Regressioncited by 62
  31. 2020Batch Normalization Embeddings for Deep Domain Generalizationcited by 57
  32. 2018Modeling Uncertainty with Hedged Instance Embeddingcited by 52
  33. 2018Classification Uncertainty of Deep Neural Networks Based on Gradient Informationcited by 43
  34. 2020A case for new neural network smoothness constraintscited by 43
  35. 2019Hybrid Models with Deep and Invertible Featurescited by 41
  36. 2018Uncertainty in the Variational Information Bottleneckcited by 39
  37. 2021Sketching Curvature for Efficient Out-of-Distribution Detection for Deep Neural Networkscited by 32
  38. 2021MixMo: Mixing Multiple Inputs for Multiple Outputs via Deep Subnetworkscited by 32

50 most cited of 56 All 56 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 11; 2023: 8; 2024: 19; 2025: 14; 2026: 8.

62 papers.

Sort:

By area:

  1. 2022SHIFT: A Synthetic Driving Dataset for Continuous Multi-Task Domain Adaptationcited by 146
  2. 2024Benchmarking Uncertainty Disentanglement: Specialized Uncertainties for Specialized Taskscited by 78
  3. 2022Trustworthy clinical AI solutions: a unified review of uncertainty quantification in deep learning models for medical image analysiscited by 62
  4. 2022Composed Image Retrieval with Text Feedback via Multi-grained Uncertainty Regularizationcited by 45
  5. 2023Quantification of Uncertainty with Adversarial Modelscited by 28
  6. 2023Introducing an Improved Information-Theoretic Measure of Predictive Uncertaintycited by 28
  7. 2024ValUES: A Framework for Systematic Validation of Uncertainty Estimation in Semantic Segmentationcited by 25
  8. 2022Interpretable Self-Aware Neural Networks for Robust Trajectory Predictioncited by 22
  9. 2023Random-Set Neural Networks (RS-NN)cited by 19
  10. 2022Latent Discriminant deterministic Uncertaintycited by 17
  11. 2022ZigZag: Universal Sampling-free Uncertainty Estimation Through Two-Step Inferencecited by 15
  12. 2023Benchmarking common uncertainty estimation methods with histopathological images under domain shift and label noisecited by 15
38 more
  1. 2021DEBOSH: Deep Bayesian Shape Optimizationcited by 14
  2. 2024Pretrained Visual Uncertaintiescited by 10
  3. 2024Epistemic Uncertainty Quantification For Pre-trained Neural Networkcited by 10
  4. 2025Uncertainty Estimation by Flexible Evidential Deep Learningcited by 10
  5. 2022Disentangling Uncertainty in Machine Translation Evaluationcited by 9
  6. 2022Towards Practical Control of Singular Values of Convolutional Layerscited by 9
  7. 2023An Informative Path Planning Framework for Active Learning in UAV-based Semantic Mappingcited by 8
  8. 2024Function Space Diversity for Uncertainty Prediction via Repulsive Last-Layer Ensemblescited by 8
  9. 2025Epistemic Artificial Intelligence is Essential for Machine Learning Models to Truly 'Know When They Do Not Know'cited by 8
  10. 2025Position: Epistemic uncertainty estimation methods are fundamentally incompletecited by 8
  11. 2023Training, Architecture, and Prior for Deterministic Uncertainty Methodscited by 7
  12. 2022Uncertainty-aware LiDAR Panoptic Segmentationcited by 6
  13. 2025Hyperdimensional Uncertainty Quantification for Multimodal Uncertainty Fusion in Autonomous Vehicles Perceptioncited by 6
  14. 2025Comparative validation of surgical phase recognition, instrument keypoint estimation, and instrument instance segmentation in endoscopy: Results of the PhaKIR 2024 challengecited by 6
  15. 2022Improving Uncertainty-based Out-of-Distribution Detection for Medical Image Segmentationcited by 5
  16. 2023Multi-layer Aggregation as a key to feature-based OOD detectioncited by 5
  17. 2023On the Calibration of Uncertainty Estimation in LiDAR-based Semantic Segmentationcited by 5
  18. 2024Geometric Transformation Uncertainty for Improving 3D Fetal Brain Pose Prediction from Freehand 2D Ultrasound Videoscited by 5
  19. 2024Uncertainty Estimation for 3D Object Detection via Evidential Learningcited by 5
  20. 2024Weakly-Supervised Residual Evidential Learning for Multi-Instance Uncertainty Estimationcited by 4
  21. 2024Transitional Uncertainty with Layered Intermediate Predictionscited by 4
  22. 2024Arctique: An artificial histopathological dataset unifying realism and controllability for uncertainty quantificationcited by 4
  23. 2025WeedsGalore: A Multispectral and Multitemporal UAV-based Dataset for Crop and Weed Segmentation in Agricultural Maize Fieldscited by 4
  24. 2024A Rate-Distortion View of Uncertainty Quantificationcited by 3
  25. 2025Uncertainty-Aware Trajectory Prediction via Rule-Regularized Heteroscedastic Deep Classificationcited by 3
  26. 2025Generative AI for Autonomous Driving: A Reviewcited by 3
  27. 2022Quantifying Model Uncertainty for Semantic Segmentation using Operators in the RKHScited by 2
  28. 2024Discriminant Distance-Aware Representation on Deterministic Uncertainty Quantification Methodscited by 2
  29. 2024Informed Spectral Normalized Gaussian Processes for Trajectory Predictioncited by 2
  30. 2025Towards Trustworthy Vital Sign Forecasting: Leveraging Uncertainty for Prediction Intervalscited by 2
  31. 2025Multi-Layer Confidence Scoring for Detection of Out-of-Distribution Samples, Adversarial Attacks, and In-Distribution Misclassificationscited by 2
  32. 2026Scalable Variational Bayesian Fine-Tuning of LLMs via Orthogonalized Low-Rank Adapterscited by 2
  33. 2024Hierarchical Insights: Exploiting Structural Similarities for Reliable 3D Semantic Segmentationcited by 1
  34. 2024Improving Deep Learning Model Calibration for Cardiac Applications using Deterministic Uncertainty Networks and Uncertainty-aware Trainingcited by 1
  35. 2024Uncertainty modeling for fine-tuned implicit functionscited by 1
  36. 2024Uncertainties of Latent Representations in Computer Visioncited by 1
  37. 2025Finer Disentanglement of Aleatoric Uncertainty Can Accelerate Chemical Histopathology Imagingcited by 1
  38. 2025Last Layer Hamiltonian Monte Carlocited by 1

50 most cited of 62 All 62 (JSON)