AI Paper Atlas

Research map / Federated learning and privacy / Personalized and heterogeneous FL

Divide, Conquer and Unite: Hierarchical Style-Recalibrated Prototype Alignment for Federated Medical Segmentation

Xingyue Zhao, Wenke Huang, Xingguang Wang, Haoyu Zhao, Linghao Zhuang, Anwen Jiang, Guancheng Wan, Mang Ye

AAAI 2026 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Federated medical and multimodal learning · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add both CDPA and FSR to FedAvg (ablation)FedAvg · Histology nuclei segmentation (avg)Dice (%): 69.50 -> 74.10Improved
add both CDPA and FSR to FedAvg (ablation)FedAvg · Prostate MRI segmentation (avg)Dice (%): 78.80 -> 82.60Improved
add only one component (CDPA or FSR) to FedAvg (ablation)FedAvg · Histology nuclei segmentation (avg)Dice (%): 69.50 -> 72.20Improved
add only the other single component to FedAvg (ablation)FedAvg · Prostate MRI segmentation (avg)Dice (%): 78.80 -> 80.10Improved
apply FSR at intermediate layers instead of input-level amplitude normalization (ablation)FedAvg · Histology nuclei segmentationDice (%)Improved
FedBCS vs FedAvgFedAvg · Histology nuclei segmentation (avg)Dice (%): 69.50 -> 74.10Improved
use prototype-based FedProto instead of FedAvgFedAvg · Prostate MRI segmentation (avg)Dice (%): 78.80 -> 77.10Hurt
use FPL instead of FedAvgFedAvg · Histology vs Prostate (avg)Dice (%): 69.50 -> 71.66 (histology); 78.80 -> 77.40 (prostate)Mixed
upload prototypes from multiple layers (4 per client) vs single-layer FPL (2 per client)FedBCS · Prostate MRI segmentationavg prototypes uploaded: 2.00 -> 4.00Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy