mlsanityData to 7 Oct 2026

Is segmentation uncertainty useful?

arXiv 2103.16265 ↗First posted 30 Mar 2021cs.CVcited by 37

Not on the map. Why?

Abstract (arXiv)

Probabilistic image segmentation encodes varying prediction confidence and inherent ambiguity in the segmentation problem. While different probabilistic segmentation models are designed to capture different aspects of segmentation uncertainty and ambiguity, these modelling differences are rarely discussed in the context of applications of uncertainty. We consider two common use cases of segmentation uncertainty, namely assessment of segmentation quality and active learning. We consider four established strategies for probabilistic segmentation, discuss their modelling capabilities, and investigate their performance in these two tasks. We find that for all models and both tasks, returned uncertainty correlates positively with segmentation error, but does not prove to be useful for active learning.

Key facts. Cited by 37 papers in the map (data through 7 Oct 2026). Builds on 7 of its 16 references that are in the map. First posted on arXiv 30 Mar 2021.

Builds on

7 of 16 references.

References · 7

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  3. 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
  4. 2018A Probabilistic U-Net for Segmentation of Ambiguous Imagescited by 281
  5. 2020Stochastic Segmentation Networks: Modelling Spatially Correlated Aleatoric Uncertaintycited by 100
  6. 2019Assessing Reliability and Challenges of Uncertainty Estimations for Medical Image Segmentationcited by 75
  7. 2016A Benchmark and Comparison of Active Learning for Logistic Regressioncited by 36

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 6; 2023: 5; 2024: 9; 2025: 9; 2026: 5.

37 papers.

Sort:

  1. 2023A review of uncertainty quantification in medical image analysis: probabilistic and non-probabilistic methodscited by 39
  2. 2024ValUES: A Framework for Systematic Validation of Uncertainty Estimation in Semantic Segmentationcited by 25
  3. 2024Tyche: Stochastic In-Context Learning for Medical Image Segmentationcited by 20
  4. 2024Conformal Semantic Image Segmentation: Post-hoc Quantification of Predictive Uncertaintycited by 19
  5. 2021Maximum Entropy on Erroneous Predictions (MEEP): Improving model calibration for medical image segmentationcited by 13
  6. 2023That Label's Got Style: Handling Label Style Bias for Uncertain Image Segmentationcited by 13
  7. 2022PatchRefineNet: Improving Binary Segmentation by Incorporating Signals from Optimal Patch-wise Binarizationcited by 6
  8. 2022Active learning using adaptable task-based prioritisationcited by 6
  9. 2024A Review of Bayesian Uncertainty Quantification in Deep Probabilistic Image Segmentationcited by 6
  10. 2021Deep Quantile Regression for Uncertainty Estimation in Unsupervised and Supervised Lesion Detectioncited by 4
  11. 2024Weakly supervised localisation of prostate cancer using reinforcement learning for bi-parametric MR imagescited by 4
  12. 2024Segmentation by registration-enabled SAM prompt engineering using five reference imagescited by 4
25 more
  1. 2024Arctique: An artificial histopathological dataset unifying realism and controllability for uncertainty quantificationcited by 4
  2. 2022Quantifying U-Net Uncertainty in Multi-Parametric MRI-based Glioma Segmentation by Spherical Image Projectioncited by 3
  3. 2023Boundary-RL: Reinforcement Learning for Weakly-Supervised Prostate Segmentation in TRUS Imagescited by 3
  4. 2025Generalizable Pancreas Segmentation via a Dual Self-Supervised Learning Frameworkcited by 3
  5. 2025Flow Stochastic Segmentation Networkscited by 3
  6. 2022Uncertainty Estimation for 3D Dense Prediction via Cross-Point Embeddingscited by 2
  7. 2025Promptable cancer segmentation using minimal expert-curated datacited by 2
  8. 2025Towards Reliable WMH Segmentation under Domain Shift: An Application Study using Maximum Entropy Regularization to Improve Uncertainty Estimationcited by 2
  9. 2021Effect of the output activation function on the probabilities and errors in medical image segmentationcited by 1
  10. 2022Distributional Gaussian Processes Layers for Out-of-Distribution Detectioncited by 1
  11. 2023Unsupervised bias discovery in medical image segmentationcited by 1
  12. 2023PULASki: Learning inter-rater variability using statistical distances to improve probabilistic segmentationcited by 1
  13. 2024Bayesian Uncertainty Estimation by Hamiltonian Monte Carlo: Applications to Cardiac MRI Segmentationcited by 1
  14. 2025SPARS: Self-Play Adversarial Reinforcement Learning for Segmentation of Liver Tumourscited by 1
  15. 2025A Probabilistic Segment Anything Model for Ambiguity-Aware Medical Image Segmentationcited by 1
  16. 2022Test-Time Mixup Augmentation for Data and Class-Specific Uncertainty Estimation in Deep Learning Image Classificationcited by 0
  17. 2024Uncertainty quantification for White Matter Hyperintensity segmentation detects silent failures and improves automated Fazekas quantificationcited by 0
  18. 2025EyeSeg: An Uncertainty-Aware Eye Segmentation Framework for AR/VRcited by 0
  19. 2025Progressive Growing of Patch Size: Curriculum Learning for Accelerated and Improved Medical Image Segmentationcited by 0
  20. 2025Pancakes: Consistent Multi-Protocol Image Segmentation Across Biomedical Domainscited by 0
  21. 2026Promptable segmentation with region exploration enables minimal-effort expert-level prostate cancer delineationcited by 0
  22. 2026Harmonized Feature Conditioning and Frequency-Prompt Personalization for Multi-Rater Medical Segmentationcited by 0
  23. 2026Confidence is Not Reliability: Rethinking MC Dropout in Brain Tumour Segmentationcited by 0
  24. 2026Active few-shot segmentation by reinforcing data selectioncited by 0
  25. 2026Bayesian adaptively-weighted ensembles for few-shot abdominal segmentationcited by 0