mlsanityData to 7 Oct 2026

Depth Uncertainty in Neural Networks

arXiv 2006.08437 ↗First posted 15 Jun 2020stat.ML cs.LGcited by 56

Not on the map. Why?

Abstract (arXiv)

Existing methods for estimating uncertainty in deep learning tend to require multiple forward passes, making them unsuitable for applications where computational resources are limited. To solve this, we perform probabilistic reasoning over the depth of neural networks. Different depths correspond to subnetworks which share weights and whose predictions are combined via marginalisation, yielding model uncertainty. By exploiting the sequential structure of feed-forward networks, we are able to both evaluate our training objective and make predictions with a single forward pass. We validate our approach on real-world regression and image classification tasks. Our approach provides uncertainty calibration, robustness to dataset shift, and accuracies competitive with more computationally expensive baselines.

Key facts. Cited by 56 papers in the map (data through 7 Oct 2026). First posted on arXiv 15 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 13; 2022: 11; 2023: 11; 2024: 14; 2025: 5; 2026: 2.

56 papers.

Sort:

By area:

  1. 2022Trusted Multi-View Classification with Dynamic Evidential Fusioncited by 167
  2. 2024To Believe or Not to Believe Your LLMcited by 120
  3. 2024TabM: Advancing Tabular Deep Learning with Parameter-Efficient Ensemblingcited by 105
  4. 2021DEUP: Direct Epistemic Uncertainty Predictioncited by 102
  5. 2021Trustworthy Multimodal Regression with Mixture of Normal-inverse Gamma Distributionscited by 39
  6. 2022UMIX: Improving Importance Weighting for Subpopulation Shift via Uncertainty-Aware Mixupcited by 34
  7. 2022Adapting the Linearised Laplace Model Evidence for Modern Deep Learningcited by 29
  8. 2023Learning Layer-wise Equivariances Automatically using Gradientscited by 23
  9. 2025Generative Uncertainty in Diffusion Modelscited by 20
  10. 2021Sparse MoEs meet Efficient Ensemblescited by 19
  11. 2022Sampling-based inference for large linear models, with application to linearised Laplacecited by 18
  12. 2023DebSDF: Delving into the Details and Bias of Neural Indoor Scene Reconstructioncited by 17
38 more
  1. 2023Towards Anytime Classification in Early-Exit Architectures by Enforcing Conditional Monotonicitycited by 16
  2. 2021Blurs Behave Like Ensembles: Spatial Smoothings to Improve Accuracy, Uncertainty, and Robustnesscited by 14
  3. 2024Enabling Uncertainty Estimation in Iterative Neural Networkscited by 11
  4. 2022Uncertainty Estimation for Computed Tomography with a Linearised Deep Image Priorcited by 10
  5. 2022Variational Inference for Infinitely Deep Neural Networkscited by 10
  6. 2021Deep Classifiers with Label Noise Modeling and Distance Awarenesscited by 8
  7. 2022Improving robustness and calibration in ensembles with diversity regularizationcited by 8
  8. 2022Bayesian Experimental Design for Computed Tomography with the Linearised Deep Image Priorcited by 7
  9. 2023Probabilistic Circuits That Know What They Don't Knowcited by 7
  10. 2021Model-Value Inconsistency as a Signal for Epistemic Uncertaintycited by 6
  11. 2022Ensembling over Classifiers: a Bias-Variance Perspectivecited by 6
  12. 2023Early-Exit Neural Networks with Nested Prediction Setscited by 6
  13. 2021Ex uno plures: Splitting One Model into an Ensemble of Subnetworkscited by 5
  14. 2024Uncertainty Estimation for 3D Object Detection via Evidential Learningcited by 5
  15. 2023Integrating Large Pre-trained Models into Multimodal Named Entity Recognition with Evidential Fusioncited by 4
  16. 2024QUTE: Quantifying Uncertainty in TinyML with Early-exit-assisted ensembles for model-monitoringcited by 4
  17. 2024Transitional Uncertainty with Layered Intermediate Predictionscited by 4
  18. 2021Addressing Bias in Active Learning with Depth Uncertainty Networks... or Notcited by 3
  19. 2022Sample-based Uncertainty Quantification with a Single Deterministic Neural Networkcited by 3
  20. 2024LightFF: Lightweight Inference for Forward-Forward Algorithmcited by 3
  21. 2024Error-Driven Uncertainty Aware Trainingcited by 3
  22. 2025Uncertainty Estimation by Human Perception versus Neural Modelscited by 3
  23. 2021Toward Accurate and Reliable Iris Segmentation Using Uncertainty Learningcited by 2
  24. 2021Depth Uncertainty Networks for Active Learningcited by 2
  25. 2022Reliable Multimodal Trajectory Prediction via Error Aligned Uncertainty Optimizationcited by 2
  26. 2023Reweighted Mixup for Subpopulation Shiftcited by 2
  27. 2023Traversing Between Modes in Function Space for Fast Ensemblingcited by 2
  28. 2024Fast Ensembling with Diffusion Schr"odinger Bridgecited by 2
  29. 2025Asymmetric Duos: Sidekicks Improve Uncertaintycited by 2
  30. 2021Can a single neuron learn predictive uncertainty?cited by 1
  31. 2021Latent Time Neural Ordinary Differential Equationscited by 1
  32. 2025Statistical Quality and Reproducibility of Pseudorandom Number Generators in Machine Learning technologiescited by 1
  33. 2026SQUAD: Scalable Quorum Adaptive Decisions via ensemble of early exit neural networkscited by 1
  34. 2021Improving Uncertainty Calibration via Prior Augmented Datacited by 0
  35. 2023Source-free Domain Adaptation Requires Penalized Diversitycited by 0
  36. 2023FineMorphs: Affine-diffeomorphic sequences for regressioncited by 0
  37. 2023Deep Active Learning with Structured Neural Depth Searchcited by 0
  38. 2024SAE: Single Architecture Ensemble Neural Networkscited by 0

50 most cited of 56 All 56 (JSON)