mlsanityData to 7 Oct 2026

Laplacian Segmentation Networks Improve Epistemic Uncertainty Quantification

arXiv 2303.13123 ↗First posted 23 Mar 2023cs.CV cs.LGcited by 9

Not on the map. Why?

Abstract (arXiv)

Image segmentation relies heavily on neural networks which are known to be overconfident, especially when making predictions on out-of-distribution (OOD) images. This is a common scenario in the medical domain due to variations in equipment, acquisition sites, or image corruptions. This work addresses the challenge of OOD detection by proposing Laplacian Segmentation Networks (LSN): methods which jointly model epistemic (model) and aleatoric (data) uncertainty for OOD detection. In doing so, we propose the first Laplace approximation of the weight posterior that scales to large neural networks with skip connections that have high-dimensional outputs. We demonstrate on three datasets that the LSN-modeled parameter distributions, in combination with suitable uncertainty measures, gives superior OOD detection.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 20 of its 37 references that are in the map. First posted on arXiv 23 Mar 2023.

Builds on

20 of 37 references.

References · 20

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  3. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  4. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  5. 2021A Survey of Uncertainty in Deep Neural Networkscited by 675
  6. 2017Skin Lesion Analysis Toward Melanoma Detection: A Challenge at the 2017 International Symposium on Biomedical Imaging (ISBI), Hosted by the International Skin Imaging Collaboration (ISIC)cited by 549
  7. 2018Identifying the Best Machine Learning Algorithms for Brain Tumor Segmentation, Progression Assessment, and Overall Survival Prediction in the BRATS Challengecited by 508
  8. 2021Laplace Redux -- Effortless Bayesian Deep Learningcited by 359
  9. 2018A Probabilistic U-Net for Segmentation of Ambiguous Imagescited by 281
  10. 2019BCN20000: Dermoscopic Lesions in the Wildcited by 224
  11. 2019PHiSeg: Capturing Uncertainty in Medical Image Segmentationcited by 128
  12. 2022Quantifying Aleatoric and Epistemic Uncertainty in Machine Learning: Are Conditional Entropy and Mutual Information Appropriate Measures?cited by 124
8 more
  1. 2020PAD-UFES-20: a skin lesion dataset composed of patient data and clinical images collected from smartphonescited by 116
  2. 2020Stochastic Segmentation Networks: Modelling Spatially Correlated Aleatoric Uncertaintycited by 100
  3. 2016Learning in an Uncertain World: Representing Ambiguity Through Multiple Hypothesescited by 96
  4. 2016Stochastic Multiple Choice Learning for Training Diverse Deep Ensemblescited by 77
  5. 2019A Hierarchical Probabilistic U-Net for Modeling Multi-Scale Ambiguitiescited by 65
  6. 2020Uncertainty quantification in medical image segmentation with normalizing flowscited by 23
  7. 2022Laplacian Autoencoders for Learning Stochastic Representationscited by 10
  8. 2021Distributional Gaussian Process Layers for Outlier Detection in Image Segmentationcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 2; 2025: 3; 2026: 3.

9 papers.

  1. 2024Out-of-distribution Detection in Medical Image Analysis: A surveycited by 22
  2. 2025Uncertainty Quantification for Machine Learning in Healthcare: A Surveycited by 11
  3. 2023Uncertainty Estimation for Safety-critical Scene Segmentation via Fine-grained Reward Maximizationcited by 7
  4. 2024A Review of Bayesian Uncertainty Quantification in Deep Probabilistic Image Segmentationcited by 6
  5. 2025Aleatoric Uncertainty Medical Image Segmentation Estimation via Flow Matchingcited by 5
  6. 2026Rethinking Uncertainty Quantification and Entanglement in Image Segmentationcited by 1
  7. 2025L-FUSION: Laplacian Fetal Ultrasound Segmentation & Uncertainty Estimationcited by 0
  8. 2026Towards Agnostic and Holistic Universal Image Segmentation with Bit Diffusioncited by 0
  9. 2026It depends: Incorporating correlations for joint aleatoric and epistemic uncertainties of high-dimensional output spacescited by 0