mlsanityData to 7 Oct 2026

FedA3I: Annotation Quality-Aware Aggregation for Federated Medical Image Segmentation against Heterogeneous Annotation Noise

arXiv 2312.12838 ↗First posted 20 Dec 2023cs.LG cs.CVcited by 14

Not on the map. Why?

Abstract (arXiv)

Federated learning (FL) has emerged as a promising paradigm for training segmentation models on decentralized medical data, owing to its privacy-preserving property. However, existing research overlooks the prevalent annotation noise encountered in real-world medical datasets, which limits the performance ceilings of FL. In this paper, we, for the first time, identify and tackle this problem. For problem formulation, we propose a contour evolution for modeling non-independent and identically distributed (Non-IID) noise across pixels within each client and then extend it to the case of multi-source data to form a heterogeneous noise model (i.e., Non-IID annotation noise across clients). For robust learning from annotations with such two-level Non-IID noise, we emphasize the importance of data quality in model aggregation, allowing high-quality clients to have a greater impact on FL. To achieve this, we propose Federated learning with Annotation quAlity-aware AggregatIon, named FedA3I, by introducing a quality factor based on client-wise noise estimation. Specifically, noise estimation at each client is accomplished through the Gaussian mixture model and then incorporated into model aggregation in a layer-wise manner to up-weight high-quality clients. Extensive experiments on two real-world medical image segmentation datasets demonstrate the superior performance of FedA3I against the state-of-the-art approaches in dealing with cross-client annotation noise. The code is available at https://github.com/wnn2000/FedAAAI.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Builds on 31 of its 44 references that are in the map. First posted on arXiv 20 Dec 2023.

Builds on

31 of 44 references.

References · 31

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  3. 2018Federated Optimization in Heterogeneous Networkscited by 2,971
  4. 2016V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentationcited by 2,284
  5. 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,053
  6. 2018Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labelscited by 994
  7. 2020DivideMix: Learning with Noisy Labels as Semi-supervised Learningcited by 691
  8. 2020The Future of Digital Health with Federated Learningcited by 625
  9. 2021FedBN: Federated Learning on Non-IID Features via Local Batch Normalizationcited by 565
  10. 2019Symmetric Cross Entropy for Robust Learning with Noisy Labelscited by 499
  11. 2020Early-Learning Regularization Prevents Memorization of Noisy Labelscited by 414
  12. 2019How does Disagreement Help Generalization against Label Corruption?cited by 390
19 more
  1. 2021FedDG: Federated Domain Generalization on Medical Image Segmentation via Episodic Learning in Continuous Frequency Spacecited by 284
  2. 2017Tversky loss function for image segmentation using 3D fully convolutional deep networkscited by 228
  3. 2019CE-Net: Context Encoder Network for 2D Medical Image Segmentationcited by 219
  4. 2022UNeXt: MLP-based Rapid Medical Image Segmentation Networkcited by 185
  5. 2021Understanding and Improving Early Stopping for Learning with Noisy Labelscited by 112
  6. 2023Federated Learning for Generalization, Robustness, Fairness: A Survey and Benchmarkcited by 97
  7. 2022Layer-wised Model Aggregation for Personalized Federated Learningcited by 95
  8. 2020Beyond Class-Conditional Assumption: A Primary Attempt to Combat Instance-Dependent Label Noisecited by 82
  9. 2021Adaptive Early-Learning Correction for Segmentation from Noisy Annotationscited by 61
  10. 2022FedCorr: Multi-Stage Federated Learning for Label Noise Correctioncited by 61
  11. 2023Fair Federated Medical Image Segmentation via Client Contribution Estimationcited by 50
  12. 2023Generalizable Heterogeneous Federated Cross-Correlation and Instance Similarity Learningcited by 39
  13. 2023FedNoRo: Towards Noise-Robust Federated Learning by Addressing Class Imbalance and Label Noise Heterogeneitycited by 33
  14. 2022Personalizing Federated Medical Image Segmentation via Local Calibrationcited by 28
  15. 2022Towards Federated Learning against Noisy Labels via Local Self-Regularizationcited by 26
  16. 2019Pick-and-Learn: Automatic Quality Evaluation for Noisy-Labeled Image Segmentationcited by 25
  17. 2021Superpixel-guided Iterative Learning from Noisy Labels for Medical Image Segmentationcited by 25
  18. 2023Learning to Segment from Noisy Annotations: A Spatial Correction Approachcited by 16
  19. 2022Federated Multi-organ Segmentation with Inconsistent Labelscited by 15

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 8; 2026: 3.

14 papers.

Sort:

  1. 2025FNBench: Benchmarking Robust Federated Learning against Noisy Labelscited by 6
  2. 2024From Optimization to Generalization: Fair Federated Learning against Quality Shift via Inter-Client Sharpness Matchingcited by 5
  3. 2024FedMLP: Federated Multi-Label Medical Image Classification under Task Heterogeneitycited by 5
  4. 2025Federated Client-tailored Adapter for Medical Image Segmentationcited by 3
  5. 2025Impact of Labeling Inaccuracy and Image Noise on Tooth Segmentation in Panoramic Radiographs using Federated, Centralized and Local Learningcited by 3
  6. 2024FedIA: Federated Medical Image Segmentation with Heterogeneous Annotation Completenesscited by 2
  7. 2025Federated Self-Supervised Learning for One-Shot Cross-Modal and Cross-Imaging Technique Segmentationcited by 1
  8. 2025Fair Federated Medical Image Classification Against Quality Shift via Inter-Client Progressive State Matchingcited by 0
  9. 2025Asynchronous Federated Continual Segmentation with Evolving Clients and Label Spacescited by 0
  10. 2025Mix-modal Federated Learning for MRI Image Segmentationcited by 0
  11. 2025Adversarial Versus Federated: An Adversarial Learning based Multi-Modality Cross-Domain Federated Medical Segmentationcited by 0
  12. 2026SplitFed-CL: A Split Federated Co-Learning Framework for Medical Image Segmentation with Inaccurate Labelscited by 0
2 more
  1. 2026Federated Medical Image Segmentation under Real-World Label Noise: A Benchmark Suite for Noisy Label Learning Method Selectioncited by 0
  2. 2026Decoupled Single-Mask Annotation Noise Detection via Cross-Sectional Patch Self-Consistencycited by 0