Towards Privacy-preserved Pre-training of Remote Sensing Foundation Models with Federated Mutual-guidance Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tan, Jieyi, Zhang, Chengwei, Dang, Bo, Li, Yansheng
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915197669605376
author Tan, Jieyi
Zhang, Chengwei
Dang, Bo
Li, Yansheng
author_facet Tan, Jieyi
Zhang, Chengwei
Dang, Bo
Li, Yansheng
contents Traditional Remote Sensing Foundation models (RSFMs) are pre-trained with a data-centralized paradigm, through self-supervision on large-scale curated remote sensing data. For each institution, however, pre-training RSFMs with limited data in a standalone manner may lead to suboptimal performance, while aggregating remote sensing data from multiple institutions for centralized pre-training raises privacy concerns. Seeking for collaboration is a promising solution to resolve this dilemma, where multiple institutions can collaboratively train RSFMs without sharing private data. In this paper, we propose a novel privacy-preserved pre-training framework (FedSense), which enables multiple institutions to collaboratively train RSFMs without sharing private data. However, it is a non-trivial task hindered by a vicious cycle, which results from model drift by remote sensing data heterogeneity and high communication overhead. To break this vicious cycle, we introduce Federated Mutual-guidance Learning. Specifically, we propose a Server-to-Clients Guidance (SCG) mechanism to guide clients updates towards global-flatness optimal solutions. Additionally, we propose a Clients-to-Server Guidance (CSG) mechanism to inject local knowledge into the server by low-bit communication. Extensive experiments on four downstream tasks demonstrate the effectiveness of our FedSense in both full-precision and communication-reduced scenarios, showcasing remarkable communication efficiency and performance gains.
format Preprint
id arxiv_https___arxiv_org_abs_2503_11051
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Towards Privacy-preserved Pre-training of Remote Sensing Foundation Models with Federated Mutual-guidance Learning
Tan, Jieyi
Zhang, Chengwei
Dang, Bo
Li, Yansheng
Computer Vision and Pattern Recognition
Traditional Remote Sensing Foundation models (RSFMs) are pre-trained with a data-centralized paradigm, through self-supervision on large-scale curated remote sensing data. For each institution, however, pre-training RSFMs with limited data in a standalone manner may lead to suboptimal performance, while aggregating remote sensing data from multiple institutions for centralized pre-training raises privacy concerns. Seeking for collaboration is a promising solution to resolve this dilemma, where multiple institutions can collaboratively train RSFMs without sharing private data. In this paper, we propose a novel privacy-preserved pre-training framework (FedSense), which enables multiple institutions to collaboratively train RSFMs without sharing private data. However, it is a non-trivial task hindered by a vicious cycle, which results from model drift by remote sensing data heterogeneity and high communication overhead. To break this vicious cycle, we introduce Federated Mutual-guidance Learning. Specifically, we propose a Server-to-Clients Guidance (SCG) mechanism to guide clients updates towards global-flatness optimal solutions. Additionally, we propose a Clients-to-Server Guidance (CSG) mechanism to inject local knowledge into the server by low-bit communication. Extensive experiments on four downstream tasks demonstrate the effectiveness of our FedSense in both full-precision and communication-reduced scenarios, showcasing remarkable communication efficiency and performance gains.
title Towards Privacy-preserved Pre-training of Remote Sensing Foundation Models with Federated Mutual-guidance Learning
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.11051