mlsanityData to 7 Oct 2026

Uncertainty Estimation by Density Aware Evidential Deep Learning

arXiv 2409.08754 ↗First posted 13 Sep 2024cs.LG stat.MLcited by 22

Not on the map. Why?

Abstract (arXiv)

Evidential deep learning (EDL) has shown remarkable success in uncertainty estimation. However, there is still room for improvement, particularly in out-of-distribution (OOD) detection and classification tasks. The limited OOD detection performance of EDL arises from its inability to reflect the distance between the testing example and training data when quantifying uncertainty, while its limited classification performance stems from its parameterization of the concentration parameters. To address these limitations, we propose a novel method called Density Aware Evidential Deep Learning (DAEDL). DAEDL integrates the feature space density of the testing example with the output of EDL during the prediction stage, while using a novel parameterization that resolves the issues in the conventional parameterization. We prove that DAEDL enjoys a number of favorable theoretical properties. DAEDL demonstrates state-of-the-art performance across diverse downstream tasks related to uncertainty estimation and classification

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). Builds on 31 of its 49 references that are in the map. First posted on arXiv 13 Sep 2024.

Builds on

31 of 49 references.

References · 31

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  2. 2017On Calibration of Modern Neural Networkscited by 4,860
  3. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  4. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  5. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  6. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  7. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  8. 2015Variational Inference with Normalizing Flowscited by 2,161
  9. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,618
  10. 2018Evidential Deep Learning to Quantify Classification Uncertaintycited by 728
  11. 2018Predictive Uncertainty Estimation via Prior Networkscited by 555
  12. 2018Deep Learning for Classical Japanese Literaturecited by 415
19 more
  1. 2020Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awarenesscited by 389
  2. 2018Regularisation of Neural Networks by Enforcing Lipschitz Continuitycited by 311
  3. 2021Deep Deterministic Uncertainty: A Simple Baselinecited by 200
  4. 2019Ensemble Distribution Distillationcited by 158
  5. 2019MNIST-C: A Robustness Benchmark for Computer Visioncited by 137
  6. 2019Reverse KL-Divergence Training of Prior Networks: Improved Uncertainty and Adversarial Robustnesscited by 104
  7. 2021On Feature Collapse and Deep Kernel Learning for Single Forward Pass Uncertaintycited by 87
  8. 2021Prior and Posterior Networks: A Survey on Evidential Deep Learning Methods For Uncertainty Estimationcited by 71
  9. 2023Uncertainty Estimation by Fisher Information-based Evidential Deep Learningcited by 58
  10. 2022Sample-dependent Adaptive Temperature Scaling for Improved Calibrationcited by 48
  11. 2020Uncertainty-Aware Deep Classifiers using Generative Modelscited by 41
  12. 2020Towards Maximizing the Representation Gap between In-Domain & Out-of-Distribution Examplescited by 40
  13. 2022Nonparametric Uncertainty Quantification for Single Deterministic Neural Networkcited by 36
  14. 2020Being Bayesian about Categorical Probabilitycited by 35
  15. 2018WAIC, but Why? Generative Ensembles for Robust Anomaly Detectioncited by 25
  16. 2022Adaptive Temperature Scaling for Robust Calibration of Deep Neural Networkscited by 24
  17. 2020Multidimensional Uncertainty-Aware Evidential Neural Networkscited by 16
  18. 2021Natural Posterior Network: Deep Bayesian Uncertainty for Exponential Family Distributionscited by 13
  19. 2022Self-Distribution Distillation: Efficient Uncertainty Estimationcited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 8; 2026: 14.

22 papers.

Sort:

By area:

  1. 2025Uncertainty Estimation by Flexible Evidential Deep Learningcited by 10
  2. 2025OCCUQ: Exploring Efficient Uncertainty Quantification for 3D Occupancy Predictioncited by 6
  3. 2025HybridFlow: Quantification of Aleatoric and Epistemic Uncertainty with a Single Hybrid Modelcited by 3
  4. 2026Multimodal Deep Generative Model for Semi-Supervised Learning under Class Imbalancecited by 3
  5. 2025Robust Adversarial Quantification via Conflict-Aware Evidential Deep Learningcited by 2
  6. 2026Evidential Transformation Network: Turning Pretrained Models into Evidential Models for Post-hoc Uncertainty Estimationcited by 2
  7. 2025Disentangling Uncertainties by Learning Compressed Data Representationcited by 1
  8. 2025Calibrating Uncertainty for Zero-Shot Adversarial CLIPcited by 1
  9. 2026GEM-FI: Gated Evidential Mixtures with Fisher Modulationcited by 1
  10. 2026Query2Uncertainty: Robust Uncertainty Quantification and Calibration for 3D Object Detection under Distribution Shiftcited by 1
  11. 2025TRUST: Test-time Resource Utilization for Superior Trustworthinesscited by 0
  12. 2025Evidential Spectrum-Aware Contrastive Learning for OOD Detection in Dynamic Graphscited by 0
10 more
  1. 2026Density-Informed Pseudo-Counts for Calibrated Evidential Deep Learningcited by 0
  2. 2026Ensemble-Based Dirichlet Modeling for Predictive Uncertainty and Selective Classificationcited by 0
  3. 2026Possibilistic Predictive Uncertainty for Deep Learningcited by 0
  4. 2026Simultaneous Long-tailed Recognition and Multi-modal Fusion for Highly Imbalanced Multi-modal Datacited by 0
  5. 2026Courtroom Analogy: New Perspective on Uncertainty-Aware Classificationcited by 0
  6. 2026DAMEL: Dual-Axis Multi-Expert Learning for Class-Imbalanced Learningcited by 0
  7. 2026AIS-Based Vessel Trajectory Prediction Using Memory-Augmented Neural Networkscited by 0
  8. 2026Function-Space Priors for Bayesian Neural ODEs with Application to Vessel Trajectory Predictioncited by 0
  9. 2026Vessel Traffic Flow Prediction on Sparse Data via Spatio-Temporal Graph Neural Networks with a Learnable Tweedie Headcited by 0
  10. 2026Multi-Field Hybrid Retrieval-Augmented Generation for Maritime Accident Root Cause Analysiscited by 0