Divide, Conquer and Unite: Hierarchical Style-Recalibrated Prototype Alignment for Federated Medical Segmentation
Not on the map. Why?
Abstract (arXiv)
Federated learning enables multiple medical institutions to train a global model without sharing data, yet feature heterogeneity from diverse scanners or protocols remains a major challenge. Many existing works attempt to address this issue by leveraging model representations (e.g., mean feature vectors) to correct local training; however, they often face two key limitations: 1) Incomplete Contextual Representation Learning: Current approaches primarily focus on final-layer features, overlooking critical multi-level cues and thus diluting essential context for accurate segmentation. 2) Layerwise Style Bias Accumulation: Although utilizing representations can partially align global features, these methods neglect domain-specific biases within intermediate layers, allowing style discrepancies to build up and reduce model robustness. To address these challenges, we propose FedBCS to bridge feature representation gaps via domain-invariant contextual prototypes alignment. Specifically, we introduce a frequency-domain adaptive style recalibration into prototype construction that not only decouples content-style representations but also learns optimal style parameters, enabling more robust domain-invariant prototypes. Furthermore, we design a context-aware dual-level prototype alignment method that extracts domain-invariant prototypes from different layers of both encoder and decoder and fuses them with contextual information for finer-grained representation alignment. Extensive experiments on two public datasets demonstrate that our method exhibits remarkable performance.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 26 of its 45 references that are in the map. First posted on arXiv 14 Nov 2025.
Builds on
26 of 45 references.
References · 26
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
- 2018Federated Optimization in Heterogeneous Networkscited by 2,971
- 2020Ditto: Fair and Robust Federated Learning Through Personalizationcited by 665
- 2016Federated Optimization: Distributed Machine Learning for On-Device Intelligencecited by 558
- 2021FedProto: Federated Prototype Learning across Heterogeneous Clientscited by 349
- 2021FedDG: Federated Domain Generalization on Medical Image Segmentation via Episodic Learning in Continuous Frequency Spacecited by 284
- 2020MS-Net: Multi-Site Network for Improving Prostate Segmentation with Heterogeneous MRI Datacited by 121
- 2021FairFed: Enabling Group Fairness in Federated Learningcited by 114
- 2019Efficient Parameter-free Clustering Using First Neighbor Relationscited by 96
- 2021Amplitude-Phase Recombination: Rethinking Robustness of Convolutional Neural Networks in Frequency Domaincited by 70
- 2021HarmoFL: Harmonizing Local and Global Drifts in Federated Learning on Heterogeneous Medical Imagescited by 62
14 more
- 2023Fair Federated Medical Image Segmentation via Client Contribution Estimationcited by 50
- 2023Generalizable Heterogeneous Federated Cross-Correlation and Instance Similarity Learningcited by 39
- 2022Personalizing Federated Medical Image Segmentation via Local Calibrationcited by 28
- 2024Fair Federated Learning under Domain Skew with Local Consistency and Domain Diversitycited by 28
- 2024Taming Cross-Domain Representation Variance in Federated Prototype Learning with Heterogeneous Data Domainscited by 27
- 2023Think Twice Before Selection: Federated Evidential Active Learning for Medical Image Analysis with Domain Shiftscited by 26
- 2023Decompose, Adjust, Compose: Effective Normalization by Playing with Frequency for Domain Generalizationcited by 25
- 2020Dataset of Segmented Nuclei in Hematoxylin and Eosin Stained Histopathology Images of 10 Cancer Typescited by 16
- 2024Contextrast: Contextual Contrastive Learning for Semantic Segmentationcited by 12
- 2025Geometric Knowledge-Guided Localized Global Distribution Alignment for Federated Learningcited by 11
- 2024Ultrasound Nodule Segmentation Using Asymmetric Learning with Simple Clinical Annotationcited by 9
- 2024SAM-Driven Weakly Supervised Nodule Segmentation with Uncertainty-Aware Cross Teachingcited by 7
- 2024WIA-LD2ND: Wavelet-based Image Alignment for Self-supervised Low-Dose CT Denoisingcited by 4
- 2025ActiveSSF: An Active-Learning-Guided Self-Supervised Framework for Long-Tailed Megakaryocyte Classificationcited by 1
Built on by
Citing papers per year: 2026: 2.
2 papers.