Research map / Federated learning and privacy / Personalized and heterogeneous FL
Fair Federated Medical Image Segmentation via Client Contribution Estimation
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use contribution-based aggregation with the multiplication combination instead of FedAvg aggregation | FedCE · Retinal Fundus Segmentation | average Dice: increase of 2.23% | Helped |
| Use contribution-based aggregation with the multiplication combination instead of FedAvg aggregation | FedCE · Retinal Fundus Segmentation | standard deviation of client Dice: decrease of 5.10 | Helped |
| Use contribution-based aggregation instead of FedAvg aggregation | FedCE · Prostate MRI Segmentation | average Dice | Helped |
| Use contribution-based aggregation instead of FedAvg aggregation | FedCE · Prostate MRI Segmentation | standard deviation of client Dice | Helped |
| Use contribution-based aggregation instead of q-FedAvg | FedCE · Retinal Fundus Segmentation | Euclidean distance to Standalone: 0.31 -> 0.17 | Helped |
| Use contribution-based aggregation instead of q-FedAvg | FedCE · Prostate MRI Segmentation | Euclidean distance to Standalone: 0.59 -> 0.49 | Helped |
| Add gradient-direction contribution estimation to data-space error estimation (ablation) | FedCE · Retinal Fundus Segmentation | segmentation performance | Helped |
| Add data-space error contribution estimation to gradient-direction contribution estimation (ablation) | FedCE · Retinal Fundus Segmentation | segmentation performance | Helped |
| Combine gradient-direction and data-space error estimates by multiplication rather than using either estimate alone (ablation) | FedCE · Prostate MRI Segmentation | segmentation performance | No clear effect |
| Combine gradient-direction and data-space error estimates by summation (ablation) | FedCE · Prostate MRI Segmentation | segmentation performance | Helped |
Closest papers by meaning
- FedA3I: Annotation Quality-Aware Aggregation for Federated Medical Image Segmentation against Heterogeneous Annotation Noise (AAAI 2024 · similarity 0.88)
- FedFACT: A Provable Framework for Controllable Group-Fairness Calibration in Federated Learning (NeurIPS 2025 · similarity 0.87)
- Dual-calibrated Co-training Framework for Personalized Federated Semi-Supervised Medical Image Segmentation (AAAI 2025 · similarity 0.87)
- FairSeg: A Large-Scale Medical Image Segmentation Dataset for Fairness Learning Using Segment Anything Model with Fair Error-Bound Scaling (ICLR 2024 · similarity 0.87)
- LoGoFair: Post-Processing for Local and Global Fairness in Federated Learning (AAAI 2025 · similarity 0.86)
- FairTrade: Achieving Pareto-Optimal Trade-Offs between Balanced Accuracy and Fairness in Federated Learning (AAAI 2024 · similarity 0.86)
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.