SAFE: Self-Adjustment Federated Learning Framework for Remote Sensing Collaborative Perception

The rapid increase in remote sensing satellites has led to the emergence of distributed space-based observation systems. However, existing distributed remote sensing models often rely on centralized training, resulting in data leakage, communication overhead, and reduced accuracy due to data distribution discrepancies across platforms. To address these challenges, we propose the $\mathit{\text{Self-Adjustment}}\mathit{\text{FEderated}}\mathit{\text{Learning}}$ (SAFE) framework, which innovatively leverages federated learning to enhance collaborative sensing in remote sensing scenarios. SAFE introduces four key strategies: (1) $\mathit{\text{Class}}\mathit{\text{Rectification}}\mathit{\text{Optimization}}$, which autonomously addresses class imbalance under unknown local and global distributions. (2) $\mathit{\text{Feature}}\mathit{\text{Alignment}}\mathit{\text{Update}}$, which mitigates Non-IID data issues via locally controlled EMA updates. (3) $\mathit{\text{Dual-Factor}}\mathit{\text{Modulation}}\mathit{\text{Rheostat}}$, which dynamically balances optimization effects during training. (4) $\mathit{\text{Adaptive}}\mathit{\text{Context}}\mathit{\text{Enhancement}}$, which is designed to improve model performance by dynamically refining foreground regions, ensuring computational efficiency with accuracy improvement across distributed satellites. Experiments on real-world image classification and object segmentation datasets validate the effectiveness and reliability of the SAFE framework in complex remote sensing scenarios.