mlsanityData to 7 Oct 2026

Density estimation in representation space to predict model uncertainty

arXiv 1908.07235 ↗First posted 20 Aug 2019cs.LG stat.MLcited by 27

Not on the map. Why?

Abstract (arXiv)

Deep learning models frequently make incorrect predictions with high confidence when presented with test examples that are not well represented in their training dataset. We propose a novel and straightforward approach to estimate prediction uncertainty in a pre-trained neural network model. Our method estimates the training data density in representation space for a novel input. A neural network model then uses this information to determine whether we expect the pre-trained model to make a correct prediction. This uncertainty model is trained by predicting in-distribution errors, but can detect out-of-distribution data without having seen any such example. We test our method for a state-of-the art image classification model in the settings of both in-distribution uncertainty estimation as well as out-of-distribution detection.

Key facts. Cited by 27 papers in the map (data through 7 Oct 2026). First posted on arXiv 20 Aug 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 3; 2023: 7; 2024: 5; 2025: 8; 2026: 1.

27 papers.

Sort:

By area:

  1. 2021A Survey of Uncertainty in Deep Neural Networkscited by 675
  2. 2023Learning to Intervene on Concept Bottleneckscited by 29
  3. 2024A Comprehensive Survey on Evidential Deep Learning and Its Applicationscited by 25
  4. 2021Gradient-Based Quantification of Epistemic Uncertainty for Deep Object Detectorscited by 16
  5. 2023Better with Less: A Data-Active Perspective on Pre-Training Graph Neural Networkscited by 14
  6. 2023Evidential Uncertainty Quantification: A Variance-Based Perspectivecited by 14
  7. 2024A Structured Review of Literature on Uncertainty in Machine Learning & Deep Learningcited by 9
  8. 2023Concurrent Misclassification and Out-of-Distribution Detection for Semantic Segmentation via Energy-Based Normalizing Flowcited by 8
  9. 2025Probabilistic Machine Learning for Noisy Labels in Earth Observationcited by 6
  10. 2022What is Flagged in Uncertainty Quantification? Latent Density Models for Uncertainty Categorizationcited by 5
  11. 2025Uncertainty-Aware Deep Learning for Wildfire Danger Forecastingcited by 4
  12. 2022TEDL: A Two-stage Evidential Deep Learning Method for Classification Uncertainty Quantificationcited by 3
15 more
  1. 2022An Exploratory Study of AI System Risk Assessment from the Lens of Data Distribution and Uncertaintycited by 3
  2. 2024Accuracy-Preserving Calibration via Statistical Modeling on Probability Simplexcited by 3
  3. 2024Understanding the Dependence of Perception Model Competency on Regions in an Imagecited by 3
  4. 2025Automated Real-time Assessment of Intracranial Hemorrhage Detection AI Using an Ensembled Monitoring Model (EMM)cited by 3
  5. 2025Mimir: Hierarchical Goal-Driven Diffusion with Uncertainty Propagation for End-to-End Autonomous Drivingcited by 3
  6. 2023Generalized Uncertainty of Deep Neural Networks: Taxonomy and Applicationscited by 2
  7. 2023Delay-SDE-net: A deep learning approach for time series modelling with memory and uncertainty estimatescited by 2
  8. 2025Quantifying Uncertainty in the Presence of Distribution Shiftscited by 2
  9. 2025Towards Reliable Time Series Forecasting under Future Uncertainty: Ambiguity and Novelty Rejection Mechanismscited by 1
  10. 2021Graceful Degradation and Related Fieldscited by 0
  11. 2023Efficient IoT Inference via Context-Awarenesscited by 0
  12. 2024Expert-aware uncertainty estimation for quality control of neural-based blood typingcited by 0
  13. 2025A Framework for Uncertainty Quantification Based on Nearest Neighbors Across Layerscited by 0
  14. 2025A Machine Learning Perspective on Automated Driving Corner Casescited by 0
  15. 2026Revisiting Neural Activation Coverage for Uncertainty Estimationcited by 0