AI RESEARCH
FedStain: Modeling Higher-Order Stain Statistics for Federated Domain Generalization in Computational Pathology
arXiv CS.CV
•
ArXi:2605.14590v1 Announce Type: new Robust whole-slide image (WSI) analysis under strict data-governance remains challenging due to substantial cross-institutional stain heterogeneity. Domain generalization (DG) mitigates these shifts but typically requires centralized data, conflicting with privacy regulations. Federated learning (FedL) provides a decentralized alternative; however, existing FedL and federated DG (FedDG) approaches rely almost exclusively on low-order statistics, assuming Gaussian-like stain distributions.