RSBuilding: Towards General Remote Sensing Image Building Extraction and Change Detection with Foundation Model

TL;DR

RSBuilding is a foundation model-based approach that unifies building extraction and change detection in remote sensing images, significantly improving cross-scene generalization and task versatility with federated training and multi-task learning.

Contribution

The paper introduces RSBuilding, a novel foundation model for remote sensing that jointly addresses building extraction and change detection, enhancing cross-scene generalization and task integration.

Findings

Achieves robust zero-shot generalization across multiple datasets.

Handles two distinct tasks simultaneously with high accuracy.

Utilizes federated training to manage incomplete supervision.

Abstract

The intelligent interpretation of buildings plays a significant role in urban planning and management, macroeconomic analysis, population dynamics, etc. Remote sensing image building interpretation primarily encompasses building extraction and change detection. However, current methodologies often treat these two tasks as separate entities, thereby failing to leverage shared knowledge. Moreover, the complexity and diversity of remote sensing image scenes pose additional challenges, as most algorithms are designed to model individual small datasets, thus lacking cross-scene generalization. In this paper, we propose a comprehensive remote sensing image building understanding model, termed RSBuilding, developed from the perspective of the foundation model. RSBuilding is designed to enhance cross-scene generalization and task universality. Specifically, we extract image features based on the prior knowledge of the foundation model and devise a multi-level feature sampler to augment scale information. To unify task representation and integrate image spatiotemporal clues, we introduce a cross-attention decoder with task prompts. Addressing the current shortage of datasets that incorporate annotations for both tasks, we have developed a federated training strategy to facilitate smooth model convergence even when supervision for some tasks is missing, thereby bolstering the complementarity of different tasks. Our model was trained on a dataset comprising up to 245,000 images and validated on multiple building extraction and change detection datasets. The experimental results substantiate that RSBuilding can concurrently handle two structurally distinct tasks and exhibits robust zero-shot generalization capabilities.