mlsanityData to 7 Oct 2026

Deep Classifiers with Label Noise Modeling and Distance Awareness

arXiv 2110.02609 ↗First posted 6 Oct 2021stat.ML cs.LGcited by 8

Not on the map. Why?

Abstract (arXiv)

Uncertainty estimation in deep learning has recently emerged as a crucial area of interest to advance reliability and robustness in safety-critical applications. While there have been many proposed methods that either focus on distance-aware model uncertainties for out-of-distribution detection or on input-dependent label uncertainties for in-distribution calibration, both of these types of uncertainty are often necessary. In this work, we propose the HetSNGP method for jointly modeling the model and data uncertainty. We show that our proposed model affords a favorable combination between these two types of uncertainty and thus outperforms the baseline methods on some challenging out-of-distribution datasets, including CIFAR-100C, ImageNet-C, and ImageNet-A. Moreover, we propose HetSNGP Ensemble, an ensembled version of our method which additionally models uncertainty over the network parameters and outperforms other ensemble baselines.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 43 of its 73 references that are in the map. First posted on arXiv 6 Oct 2021.

Builds on

43 of 73 references.

References · 43

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  4. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  5. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  6. 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,274
  7. 2015Optimizing Neural Networks with Kronecker-factored Approximate Curvaturecited by 776
  8. 2018Evidential Deep Learning to Quantify Classification Uncertaintycited by 728
  9. 2018Predictive Uncertainty Estimation via Prior Networkscited by 555
  10. 2015Weight Uncertainty in Neural Networkscited by 554
  11. 2015Deep Kernel Learningcited by 440
  12. 2020Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awarenesscited by 389
31 more
  1. 2018Invertible Residual Networkscited by 364
  2. 2020Are we done with ImageNet?cited by 329
  3. 2021Exploring the Limits of Out-of-Distribution Detectioncited by 283
  4. 2020Training independent subnetworks for robust predictioncited by 177
  5. 2020Posterior Network: Uncertainty Estimation without OOD Samples via Density-Based Pseudo-Countscited by 163
  6. 2019Ensemble Distribution Distillationcited by 158
  7. 2017Practical Gauss-Newton Optimisation for Deep Learningcited by 139
  8. 2021Bayesian Neural Network Priors Revisitedcited by 121
  9. 2018High-Quality Prediction Intervals for Deep Learning: A Distribution-Free, Ensembled Approachcited by 117
  10. 2021Scalable Marginal Likelihood Estimation for Model Selection in Deep Learningcited by 105
  11. 2019Reverse KL-Divergence Training of Prior Networks: Improved Uncertainty and Adversarial Robustnesscited by 104
  12. 2021Repulsive Deep Ensembles are Bayesiancited by 103
  13. 2021Priors in Bayesian Deep Learning: A Reviewcited by 101
  14. 2020Stochastic Segmentation Networks: Modelling Spatially Correlated Aleatoric Uncertaintycited by 100
  15. 2021On Feature Collapse and Deep Kernel Learning for Single Forward Pass Uncertaintycited by 87
  16. 2021Uncertainty Baselines: Benchmarks for Uncertainty & Robustness in Deep Learningcited by 81
  17. 2020Confidence Scores Make Instance-dependent Label-noise Learning Possiblecited by 63
  18. 2019A Systematic Comparison of Bayesian Deep Learning Robustness in Diabetic Retinopathy Taskscited by 62
  19. 2020Depth Uncertainty in Neural Networkscited by 56
  20. 2020A statistical theory of cold posteriors in deep neural networkscited by 53
  21. 2018Dirichlet-based Gaussian Processes for Large-scale Calibrated Classificationcited by 50
  22. 2019Analyzing the Role of Model Uncertainty for Electronic Health Recordscited by 41
  23. 2020Towards Maximizing the Representation Gap between In-Domain & Out-of-Distribution Examplescited by 40
  24. 2021Correlated Input-Dependent Label Noise in Large-Scale Image Classificationcited by 37
  25. 2020Hydra: Preserving Ensemble Diversity for Model Distillationcited by 31
  26. 2020Fast Predictive Uncertainty for Classification with Bayesian Deep Networkscited by 31
  27. 2021Exact Langevin Dynamics with Stochastic Gradientscited by 30
  28. 2020Cold Posteriors and Aleatoric Uncertaintycited by 22
  29. 2021On Stein Variational Neural Network Ensemblescited by 21
  30. 2021BNNpriors: A library for Bayesian neural network inference with different prior distributionscited by 20
  31. 2019Output-Constrained Bayesian Neural Networkscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 4; 2024: 0; 2025: 2; 2026: 1.

8 papers.

  1. 2022Assaying Out-Of-Distribution Generalization in Transfer Learningcited by 53
  2. 2023Massively Scaling Heteroscedastic Classifierscited by 11
  3. 2023Understanding Pathologies of Deep Heteroskedastic Regressioncited by 9
  4. 2023Logistic-Normal Likelihoods for Heteroscedastic Label Noisecited by 3
  5. 2025Uncertainty-Aware Trajectory Prediction via Rule-Regularized Heteroscedastic Deep Classificationcited by 3
  6. 2023Transferable Candidate Proposal with Bounded Uncertaintycited by 2
  7. 2025On the Effect of Regularization on Nonparametric Mean-Variance Regressioncited by 0
  8. 2026Flexible Spectral-Normalized Neural Gaussian Process for Dynamic Aperture Predictioncited by 0