Bridging Data Islands: Geographic Heterogeneity-Aware Federated Learning for Collaborative Remote Sensing Semantic Segmentation

2024-04-14

arXiv.org

AI Summary

To address the “data silos” and privacy-preserving challenges in remote sensing semantic segmentation caused by geographical heterogeneity, this paper proposes GeoFed, a geographical heterogeneity-aware federated learning framework. We systematically decouple two distinct sources of geographical heterogeneity—class distribution shift and target appearance variation—for the first time. GeoFed introduces three core components: a Geographical Information Encoder (GIE) to incorporate spatial priors, an Essential Feature Mining module (EFM) for robust feature extraction under heterogeneous appearances, and a Local-Global balanced Optimizer (LoGo) enabling adaptive local regularization guided by global knowledge. Evaluated on three benchmark remote sensing federated learning datasets—FedFBP, FedCASID, and FedInria—GeoFed achieves average mIoU improvements of 3.2–5.8 percentage points over state-of-the-art methods, demonstrating both the effectiveness of explicit geographical heterogeneity modeling and strong generalization across diverse geographic domains.

Technology Category

• Computer Vision: Remote Sensing / Geospatial AI
• Machine Learning: Distributed Machine Learning & Federated Learning
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing

Abstract

Remote sensing semantic segmentation (RSS) is an essential technology in earth observation missions. Due to concerns over geographic information security, data privacy, storage bottleneck and industry competition, high-quality annotated remote sensing images are often isolated and distributed across institutions. The issue of remote sensing data islands poses challenges for fully utilizing isolated datasets to train a global model. Federated learning (FL), a privacy-preserving distributed collaborative learning technology, offers a potential solution to leverage isolated remote sensing data. Typically, remote sensing images from different institutions exhibit significant geographic heterogeneity, characterized by coupled class-distribution heterogeneity and object-appearance heterogeneity. However, existing FL methods lack consideration of them, leading to a decline in the performance of the global model when FL is directly applied to RSS. We propose a novel Geographic heterogeneity-aware Federated learning (GeoFed) framework to bridge data islands in RSS. Our framework consists of three modules, including the Global Insight Enhancement (GIE) module, the Essential Feature Mining (EFM) module and the Local-Global Balance (LoGo) module. Through the GIE module, class distribution heterogeneity is alleviated by introducing a prior global class distribution vector. We design an EFM module to alleviate object appearance heterogeneity by constructing essential features. Furthermore, the LoGo module enables the model to possess both global generalization capability and local adaptation. Extensive experiments on three public datasets (i.e., FedFBP, FedCASID, FedInria) demonstrate that our GeoFed framework consistently outperforms the current state-of-the-art methods.

Problem

• Federated Learning
• Remote Sensing
• Privacy Preservation

Innovation

• GeoFed
• Federated Learning
• Remote Sensing Semantic Segmentation