AI Paper Atlas

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

OmniFM: Toward Modality-Robust and Task-Agnostic Federated Learning for Heterogeneous Medical Imaging

Meilin Liu, Jiaying Wang, Jing Shan

CVPR 2026 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Federated medical and multimodal learning · 0 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
use OmniFM spectral retrieval framework instead of FedPerFedPer · Cross-modality classification (Scenario 1, 20%)accuracy (%): 84.47 -> 96.85Improved
use OmniFM instead of FedPerFedPer · BreaKHis super-resolution (Scenario 1)PSNR (dB): 32.99 -> 35.79Improved
use OmniFM instead of FedPerFedPer · FeTS2022 segmentationDice (%): 73.86 -> 77.41Improved
use OmniFM instead of FedAvgFedAvg · Multi-modal fusion (avg of 3 clients)VIF: 0.279 -> 0.269Hurt
use OmniFM instead of FedPerFedPer · Federated medical VQA Task 1 (SLAKE)accuracy: F-2stage non-IID 0.824 -> 0.840; F-CL non-IID 0.833 -> 0.831Mixed
use OmniFM instead of FedPerFedPer · Federated medical VQA Task 3 (Full Tuning)average accuracy: 46.03 -> 47.30Improved
add Global Spectral Knowledge Retrieval (ablation)OmniFM · Cross-modality classification (ablation)accuracy (%): 95.82 -> 97.82Improved
add embedding-wise cross-attention (ablation)OmniFM · Super-resolution (ablation)PSNR (dB): 35.04 -> 35.79Improved
add prefix-suffix prompting (ablation)OmniFM · Federated medical VQA Task 2 (ablation)accuracy: 79.42 -> 79.27No clear effect
add prefix-suffix prompting (ablation)OmniFM · Cross-modality classification (ablation)accuracy (%): 96.92 -> 97.82Improved
add Spectral-Proximal Alignment (ablation)OmniFM · Federated medical VQA Task 2 (ablation)accuracy: 77.64 -> 79.27Improved
add Spectral-Proximal Alignment (ablation)OmniFM · Federated medical VQA Task 3 (ablation)accuracy: 42.37 -> 44.21Improved

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