mlsanityData to 7 Oct 2026

Gaussian Latent Representations for Uncertainty Estimation using Mahalanobis Distance in Deep Classifiers

arXiv 2305.13849 ↗First posted 23 May 2023cs.CV cs.LGcited by 10

Not on the map. Why?

Abstract (arXiv)

Recent works show that the data distribution in a network's latent space is useful for estimating classification uncertainty and detecting Out-of-distribution (OOD) samples. To obtain a well-regularized latent space that is conducive for uncertainty estimation, existing methods bring in significant changes to model architectures and training procedures. In this paper, we present a lightweight, fast, and high-performance regularization method for Mahalanobis distance-based uncertainty prediction, and that requires minimal changes to the network's architecture. To derive Gaussian latent representation favourable for Mahalanobis Distance calculation, we introduce a self-supervised representation learning method that separates in-class representations into multiple Gaussians. Classes with non-Gaussian representations are automatically identified and dynamically clustered into multiple new classes that are approximately Gaussian. Evaluation on standard OOD benchmarks shows that our method achieves state-of-the-art results on OOD detection with minimal inference time, and is very competitive on predictive probability calibration. Finally, we show the applicability of our method to a real-life computer vision use case on microorganism classification.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 36 of its 57 references that are in the map. First posted on arXiv 23 May 2023.

Builds on

36 of 57 references.

References · 36

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  3. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  4. 2017On Calibration of Modern Neural Networkscited by 4,860
  5. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  6. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  7. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  8. 2016Wide Residual Networkscited by 3,057
  9. 2017Billion-scale similarity search with GPUscited by 2,477
  10. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  11. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
  12. 2019Natural Adversarial Examplescited by 1,401
24 more
  1. 2020Energy-based Out-of-distribution Detectioncited by 1,296
  2. 2017A Survey on Deep Learning in Medical Image Analysiscited by 1,182
  3. 2018Deep Clustering for Unsupervised Learning of Visual Featurescited by 1,020
  4. 2019Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methodscited by 903
  5. 2020A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challengescited by 813
  6. 2018Evidential Deep Learning to Quantify Classification Uncertaintycited by 728
  7. 2021A Survey of Uncertainty in Deep Neural Networkscited by 675
  8. 2018Predictive Uncertainty Estimation via Prior Networkscited by 555
  9. 2019A Survey of Deep Learning Techniques for Autonomous Drivingcited by 401
  10. 2020Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awarenesscited by 389
  11. 2014Stochastic Gradient Hamiltonian Monte Carlocited by 341
  12. 2020Hands-on Bayesian Neural Networks -- a Tutorial for Deep Learning Userscited by 336
  13. 2021Exploring the Limits of Out-of-Distribution Detectioncited by 283
  14. 2021A Simple Fix to Mahalanobis Distance for Improving Near-OOD Detectioncited by 206
  15. 2018Understanding Measures of Uncertainty for Adversarial Example Detectioncited by 177
  16. 2020Bayesian Neural Networks: An Introduction and Surveycited by 130
  17. 2021On Feature Collapse and Deep Kernel Learning for Single Forward Pass Uncertaintycited by 87
  18. 2020Why is the Mahalanobis Distance Effective for Anomaly Detection?cited by 28
  19. 2019Fine-Grained Segmentation Networks: Self-Supervised Segmentation for Improved Long-Term Visual Localizationcited by 24
  20. 2020The Hidden Uncertainty in a Neural Networks Activationscited by 14
  21. 2017Incorporating Intra-Class Variance to Fine-Grained Visual Recognitioncited by 11
  22. 2021Intraclass clustering: an implicit learning ability that regularizes DNNscited by 6
  23. 2021Tackling Inter-Class Similarity and Intra-Class Variance for Microscopic Image-based Classificationcited by 6
  24. 2021Anomaly Detection in Image Datasets Using Convolutional Neural Networks, Center Loss, and Mahalanobis Distancecited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 6; 2026: 3.

10 papers.

  1. 2025Probabilistic Embeddings for Frozen Vision-Language Models: Uncertainty Quantification with Gaussian Process Latent Variable Modelscited by 9
  2. 2024Adversarially Robust Out-of-Distribution Detection Using Lyapunov-Stabilized Embeddingscited by 6
  3. 2025Leveraging Intermediate Representations for Better Out-of-Distribution Detectioncited by 5
  4. 2025Distance-informed Neural Processescited by 3
  5. 2025ZClassifier: Temperature Tuning and Manifold Approximation via KL Divergence on Logit Spacecited by 0
  6. 2025Towards Robust Artificial Intelligence: Self-Supervised Learning Approach for Out-of-Distribution Detectioncited by 0
  7. 2025Uncertainty-aware Physics-informed Neural Networks for Robust CARS-to-Raman Signal Reconstructioncited by 0
  8. 2026From Calibration to Refinement: Seeking Certainty via Probabilistic Evidence Propagation for Noisy-Label Person Re-Identificationcited by 0
  9. 2026Ranked Activation Shift for Post-Hoc Out-of-Distribution Detectioncited by 0
  10. 2026ADAPTOOD: Uncertainty-Aware Fine-Tuning for Out-of-Distribution ECG Time Series Modelscited by 0