Research map / Federated learning and privacy / Personalized and heterogeneous FL
FedDG: Federated Domain Generalization on Medical Image Segmentation via Episodic Learning in Continuous Frequency Space
Check 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 |
|---|---|---|---|
| Add continuous frequency space interpolation (CFSI) to FedDG training (ablation) | ELCFS · Unseen domains in fundus and prostate segmentation | generalization performance | Helped |
| Add boundary-oriented episodic learning (BEL) (ablation) | ELCFS · Unseen domains in fundus and prostate segmentation | generalization performance | Helped |
| Use a fixed positive interpolation ratio instead of no distribution transfer (λ=0) (ablation) | ELCFS · Fundus optic disc segmentation | generalization performance | Helped |
| Continuously sample λ rather than use a fixed interpolation ratio (ablation) | ELCFS · Fundus optic disc segmentation | generalization performance | Helped |
| Sample λ from [0.0, 1.0] rather than the narrower tested ranges (ablation) | ELCFS · Fundus optic disc segmentation | generalization performance | Helped |
| Add the boundary-oriented objective to meta optimization (ablation) | ELCFS · Fundus and prostate segmentation | generalization performance | Helped |
| Increase the number of participating federated clients (ablation) | ELCFS and FedAvg · Prostate MRI, unseen Sites A and B | generalization performance | Helped |
| Use ELCFS instead of FedAvg | Federated fundus optic disc segmentation · Unseen sites, overall | Dice: +2.02% | Helped |
| Use ELCFS instead of FedAvg | Federated fundus optic disc segmentation · Unseen sites, overall | HD: 2.86 | Helped |
| Use ELCFS instead of FedAvg | Federated prostate MRI segmentation · Unseen sites, average | Dice: 85.57% to 87.39% | Helped |
| Use ELCFS instead of FedAvg | Federated prostate MRI segmentation · Unseen sites, average | HD: 12.42 to 10.88 | Helped |
Closest papers by meaning
- FedVCK: Non-IID Robust and Communication-Efficient Federated Learning via Valuable Condensed Knowledge for Medical Image Analysis (AAAI 2025 · similarity 0.88)
- Dual-calibrated Co-training Framework for Personalized Federated Semi-Supervised Medical Image Segmentation (AAAI 2025 · similarity 0.87)
- FedA3I: Annotation Quality-Aware Aggregation for Federated Medical Image Segmentation against Heterogeneous Annotation Noise (AAAI 2024 · similarity 0.87)
- Federated Black-Box Adaptation for Semantic Segmentation (NeurIPS 2024 · similarity 0.86)
- FedST: Federated Style Transfer Learning for Non-IID Image Segmentation (AAAI 2024 · similarity 0.86)
- Think Twice Before Selection: Federated Evidential Active Learning for Medical Image Analysis with Domain Shifts (CVPR 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.