FedAdapt: Unsupervised Federated Domain Adaptation for Cross-Satellite Hyperspectral Image Classification

Authors:
Publisher website
Google Scholar
Abstract
Multi-satellite hyperspectral image classification is increasingly expected to be performed on-orbit to reduce downlink and annotation costs. However, existing unsupervised domain adaptation methods typically rely on the closed-set assumption that source and target domains share the same label space, which is often violated in real multi-satellite deployments due to temporal land-cover changes and sensor upgrades. When the target domain contains previously unseen classes, directly aligning the two domains may induce negative transfer, making it difficult to learn a reliable decision boundary between known and unknown categories, especially under privacy constraints that prohibit raw data sharing. To address these challenges, we propose FedAdapt, an open-set unsupervised federated domain adaptation framework for cross-satellite hyperspectral image classification. FedAdapt first constructs class prototype vectors to induce a discriminative metric space for known classes and estimates an instance-level reliability weight for each target sample by its similarity to the prototypes. Based on this reliability, a relevance-driven weighting strategy is introduced to perform cautious adversarial domain alignment, emphasizing likely-known target samples while suppressing potential unknowns to mitigate negative transfer. In addition, an energy-based dynamic thresholding scheme is learned to adaptively separate known and unknown target samples without manual threshold tuning. Experimental results on multiple cross-scene HSI classification tasks demonstrate the effectiveness of our method.
Funding Information
  • National Natural Science Foundation of China (U25A20528)
  • National Natural Science Foundation of China (62406233)
  • National Natural Science Foundation of China (62576259)
  • Science and Technology Breakthrough Project of Inner Mongolia Autonomous Region (2025KJTW0026)
  • Fundamental Research Funds for the Central Universities
  • National Natural Science Foundation of China (LP180100114)
  • National Natural Science Foundation of China (DP200102611)

This publication has 58 references indexed in Scilit: