mlsanityData to 7 Oct 2026

Learning to Segment from Noisy Annotations: A Spatial Correction Approach

arXiv 2308.02498 ↗First posted 21 Jul 2023eess.IV cs.CV cs.LGcited by 16

Not on the map. Why?

Abstract (arXiv)

Noisy labels can significantly affect the performance of deep neural networks (DNNs). In medical image segmentation tasks, annotations are error-prone due to the high demand in annotation time and in the annotators' expertise. Existing methods mostly assume noisy labels in different pixels are textiti.i.d. However, segmentation label noise usually has strong spatial correlation and has prominent bias in distribution. In this paper, we propose a novel Markov model for segmentation noisy annotations that encodes both spatial correlation and bias. Further, to mitigate such label noise, we propose a label correction method to recover true label progressively. We provide theoretical guarantees of the correctness of the proposed method. Experiments show that our approach outperforms current state-of-the-art methods on both synthetic and real-world noisy annotations.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). Builds on 26 of its 49 references that are in the map. First posted on arXiv 21 Jul 2023.

Builds on

26 of 49 references.

References · 26

  1. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  2. 2016Understanding deep learning requires rethinking generalizationcited by 1,657
  3. 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,053
  4. 2018Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labelscited by 994
  5. 2017A Closer Look at Memorization in Deep Networkscited by 936
  6. 2020DivideMix: Learning with Noisy Labels as Semi-supervised Learningcited by 691
  7. 2016Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approachcited by 663
  8. 2017MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labelscited by 652
  9. 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
  10. 2018Identifying the Best Machine Learning Algorithms for Brain Tumor Segmentation, Progression Assessment, and Overall Survival Prediction in the BRATS Challengecited by 508
  11. 2019Symmetric Cross Entropy for Robust Learning with Noisy Labelscited by 499
  12. 2020Early-Learning Regularization Prevents Memorization of Noisy Labelscited by 414
14 more
  1. 2019How does Disagreement Help Generalization against Label Corruption?cited by 390
  2. 2018Joint Optimization Framework for Learning with Noisy Labelscited by 293
  3. 2018A Probabilistic U-Net for Segmentation of Ambiguous Imagescited by 281
  4. 2020Normalized Loss Functions for Deep Learning with Noisy Labelscited by 257
  5. 2018Using Trusted Data to Train Deep Networks on Labels Corrupted by Severe Noisecited by 216
  6. 2019Peer Loss Functions: Learning from Noisy Labels without Knowing Noise Ratescited by 142
  7. 2021Learning with Feature-Dependent Label Noise: A Progressive Approachcited by 102
  8. 2019Curriculum Loss: Robust Learning and Generalization against Label Corruptioncited by 87
  9. 2020Error-Bounded Correction of Noisy Labelscited by 74
  10. 2021Adaptive Early-Learning Correction for Segmentation from Noisy Annotationscited by 61
  11. 2020Disentangling Human Error from the Ground Truth in Segmentation of Medical Imagescited by 58
  12. 2021Open-set Label Noise Can Improve Robustness Against Inherent Label Noisecited by 58
  13. 2019Pick-and-Learn: Automatic Quality Evaluation for Noisy-Labeled Image Segmentationcited by 25
  14. 2021Superpixel-guided Iterative Learning from Noisy Labels for Medical Image Segmentationcited by 25

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 2; 2025: 5; 2026: 6.

16 papers.

Sort:

By area:

  1. 2023FedA3I: Annotation Quality-Aware Aggregation for Federated Medical Image Segmentation against Heterogeneous Annotation Noisecited by 14
  2. 2024BadCLM: Backdoor Attack in Clinical Language Models for Electronic Health Recordscited by 5
  3. 2023Improving Multiple Sclerosis Lesion Segmentation Across Clinical Sites: A Federated Learning Approach with Noise-Resilient Trainingcited by 4
  4. 2026Towards Fairness under Label Bias in Image Segmentation: Impact, Measurement and Mitigationcited by 2
  5. 2025The Accuracy Cost of Weakness: A Theoretical Analysis of Fixed-Segment Weak Labeling for Events in Timecited by 1
  6. 2025A Bayesian Approach to Segmentation with Noisy Labels via Spatially Correlated Distributionscited by 1
  7. 2025From Noisy Labels to Intrinsic Structure: A Geometric-Structural Dual-Guided Framework for Noise-Robust Medical Image Segmentationcited by 1
  8. 2025Segment-to-Act: Label-Noise-Robust Action-Prompted Video Segmentation Towards Embodied Intelligencecited by 1
  9. 2023Clean Label Disentangling for Medical Image Segmentation with Noisy Labelscited by 0
  10. 2024How Much Data are Enough? Investigating Dataset Requirements for Patch-Based Brain MRI Segmentation Taskscited by 0
  11. 2025Monitoring morphometric drift in lifelong learning segmentation of the spinal cordcited by 0
  12. 2026Generalizing Abstention for Noise-Robust Learning in Medical Image Segmentationcited by 0
4 more
  1. 2026Decoupled Single-Mask Annotation Noise Detection via Cross-Sectional Patch Self-Consistencycited by 0
  2. 2026Align and Segment: Unsupervised Learning for Building Segmentation From Misaligned Labelscited by 0
  3. 2026Expert-like Bone Ultrasound Segmentation through Expert-in-the-loop Mask-conditioned Progressive Learningcited by 0
  4. 2026VoxelFix: Post-Hoc Semantic Correction of Completed 3D Voxel Mapscited by 0