Free lunch for federated remote sensing target fine-grained classification: A parameter-efficient framework

Shengchao Chen, Ting Shu, Huan Zhao, Jiahao Wang, Sufen Ren, Lina Yang

Abstract: Highlights•Introduced a privacy-focused framework for fine-grained remote sensing task classification.•Developed a unique knowledge distillation method for private, tailored client learning.•Implemented dynamic parameter decomposition to slash communication overhead and boost efficiency.•Our method excels in real-world tests, surpassing current FL methods in efficiency and performance.