Saved in:
Bibliographic Details
Main Authors: Liu, Meilin, Wang, Jiaying, Shan, Jing
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.21660
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908906758864896
author Liu, Meilin
Wang, Jiaying
Shan, Jing
author_facet Liu, Meilin
Wang, Jiaying
Shan, Jing
contents Federated learning (FL) has become a promising paradigm for collaborative medical image analysis, yet existing frameworks remain tightly coupled to task-specific backbones and are fragile under heterogeneous imaging modalities. Such constraints hinder real-world deployment, where institutions vary widely in modality distributions and must support diverse downstream tasks. To address this limitation, we propose OmniFM, a modality- and task-agnostic FL framework that unifies training across classification, segmentation, super-resolution, visual question answering, and multimodal fusion without re-engineering the optimization pipeline. OmniFM builds on a key frequency-domain insight: low-frequency spectral components exhibit strong cross-modality consistency and encode modality-invariant anatomical structures. Accordingly, OmniFM integrates (i) Global Spectral Knowledge Retrieval to inject global frequency priors, (ii) Embedding-wise Cross-Attention Fusion to align representations, and (iii) Prefix-Suffix Spectral Prompting to jointly condition global and personalized cues, together regularized by a Spectral-Proximal Alignment objective that stabilizes aggregation. Experiments on real-world datasets show that OmniFM consistently surpasses state-of-the-art FL baselines across intra- and cross-modality heterogeneity, achieving superior results under both fine-tuning and training-from-scratch setups.
format Preprint
id arxiv_https___arxiv_org_abs_2603_21660
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle OmniFM: Toward Modality-Robust and Task-Agnostic Federated Learning for Heterogeneous Medical Imaging
Liu, Meilin
Wang, Jiaying
Shan, Jing
Computer Vision and Pattern Recognition
Federated learning (FL) has become a promising paradigm for collaborative medical image analysis, yet existing frameworks remain tightly coupled to task-specific backbones and are fragile under heterogeneous imaging modalities. Such constraints hinder real-world deployment, where institutions vary widely in modality distributions and must support diverse downstream tasks. To address this limitation, we propose OmniFM, a modality- and task-agnostic FL framework that unifies training across classification, segmentation, super-resolution, visual question answering, and multimodal fusion without re-engineering the optimization pipeline. OmniFM builds on a key frequency-domain insight: low-frequency spectral components exhibit strong cross-modality consistency and encode modality-invariant anatomical structures. Accordingly, OmniFM integrates (i) Global Spectral Knowledge Retrieval to inject global frequency priors, (ii) Embedding-wise Cross-Attention Fusion to align representations, and (iii) Prefix-Suffix Spectral Prompting to jointly condition global and personalized cues, together regularized by a Spectral-Proximal Alignment objective that stabilizes aggregation. Experiments on real-world datasets show that OmniFM consistently surpasses state-of-the-art FL baselines across intra- and cross-modality heterogeneity, achieving superior results under both fine-tuning and training-from-scratch setups.
title OmniFM: Toward Modality-Robust and Task-Agnostic Federated Learning for Heterogeneous Medical Imaging
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.21660