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

TL;DR

This paper introduces GeoFed, a federated learning framework designed to address geographic heterogeneity in remote sensing data, improving semantic segmentation performance across isolated datasets while preserving privacy.

Contribution

The paper presents a novel GeoFed framework with three modules that explicitly handle class distribution and object appearance heterogeneity in federated remote sensing tasks.

Findings

GeoFed outperforms existing methods on three public datasets.

The framework effectively mitigates data heterogeneity issues.

Results show improved global model accuracy and robustness.

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.