Prototype-Aligned Federated Learning for Robust Object Extraction in Heterogeneous Remote Sensing

Federated learning (FL) has emerged as a pivotal collaborative machine learning framework, enabling privacy-preserving analytics for smart city applications using distributed data from Internet of Things (IoT) devices. However, the inherent data heterogeneity that arises from diverse geographical and environmental factors poses significant challenges to the effectiveness of FL-based models. To address these challenges, this article introduces a novel Prototype-Based FL framework for cross-domain object extraction in heterogeneous remote sensing images. The proposed framework employs multiple vectors to represent class prototypes for capturing the intricate intraclass variations and mitigating the adverse effects of nonidentically distributed (non-IID) data across clients. Furthermore, we adopt a distance-based classification method to reduce classification errors. Additionally, we propose a Prototype-Anchored Metric Learning approach to minimize intraclass variance and enhance interclass separability, which can facilitate the alignment of feature representations across heterogeneous datasets. The proposed method improves the coherence and stability of feature spaces in federated settings and enhances the global model’s generalization capabilities for complex urban monitoring tasks. Extensive experiments on three distinct remote sensing datasets (including infrastructure and disaster) demonstrate that the proposed method significantly outperforms state-of-the-art FL-based approaches in urban monitoring accuracy and robustness. The code is available at https://github.com/beifang2/FedPARS.