Research map / Federated learning and privacy / Personalized and heterogeneous FL
Personalizing Federated Medical Image Segmentation via Local Calibration
Jiacheng Wang, Yueming Jin, Liansheng Wang
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add PCS module to FedRep (ablation) | FedRep · PMR | average IoU: 81.13 -> 82.97 | Improved |
| add PCS module to FedRep (ablation) | FedRep · EndoPolyp | average IoU: 72.56 -> 73.57 | Improved |
| add PCS module to FedRep (ablation) | FedRep · RIF | average IoU: 83.15 -> 83.47 | Improved |
| add HC module to FedRep (ablation) | FedRep · PMR | average IoU: 81.13 -> 81.65 | Improved |
| add HC module to FedRep (ablation) | FedRep · EndoPolyp | average IoU: 72.56 -> 72.21 | Hurt |
| add HC module to FedRep (ablation) | FedRep · RIF | average IoU: 83.15 -> 84.10 | Improved |
| add HC module on top of PCS (ablation) | LC-Fed · EndoPolyp | average IoU: 73.57 -> 75.63 | Improved |
| add PCS module on top of HC (ablation) | LC-Fed · RIF | average IoU: 84.10 -> 85.05 | Improved |
| add PCS module to FedRep on RIF ASSD (ablation) | FedRep · RIF | average ASSD: 3.88 -> 4.23 | Hurt |
| add NMS operator in head calibration (ablation) | LC-Fed · EndoPolyp | average IoU: 74.92 -> 75.63 | Improved |
| use same site embeddings for all sites and no site-contrast regularization instead of contrastive embeddings (ablation) | LC-Fed · PMR, EndoPolyp, RIF | IoU | Improved |
| use site-contrast regularization lambda 0.1 instead of 0 (ablation) | LC-Fed · PMR | IoU | Improved |
Closest papers by meaning
- Dual-calibrated Co-training Framework for Personalized Federated Semi-Supervised Medical Image Segmentation (AAAI 2025 · similarity 0.91)
- FedA3I: Annotation Quality-Aware Aggregation for Federated Medical Image Segmentation against Heterogeneous Annotation Noise (AAAI 2024 · similarity 0.87)
- Federated Modality-Specific Encoders and Multimodal Anchors for Personalized Brain Tumor Segmentation (AAAI 2024 · similarity 0.87)
- FedVCK: Non-IID Robust and Communication-Efficient Federated Learning via Valuable Condensed Knowledge for Medical Image Analysis (AAAI 2025 · similarity 0.84)
- Diversified and Personalized Multi-rater Medical Image Segmentation (CVPR 2024 · similarity 0.84)
- MH-pFLID: Model Heterogeneous personalized Federated Learning via Injection and Distillation for Medical Data Analysis (ICML 2024 · similarity 0.84)
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.
