SegChange-R1: LLM-Augmented Remote Sensing Change Detection

TL;DR

SegChange-R1 introduces an LLM-augmented approach for remote sensing change detection, integrating textual info and spatial transformations to improve accuracy and convergence, supported by a new UAV building change dataset.

Contribution

The paper presents a novel LLM-augmented inference method with a BEV spatial module and a new UAV building change dataset, advancing remote sensing change detection techniques.

Findings

Significant performance improvements over existing methods.

Effective integration of textual descriptions enhances detection accuracy.

The BEV module addresses modal misalignment effectively.

Abstract

Remote sensing change detection is used in urban planning, terrain analysis, and environmental monitoring by analyzing feature changes in the same area over time. In this paper, we propose a large language model (LLM) augmented inference approach (SegChange-R1), which enhances the detection capability by integrating textual descriptive information and guides the model to focus on relevant change regions, accelerating convergence. We designed a linear attention-based spatial transformation module (BEV) to address modal misalignment by unifying features from different times into a BEV space. Furthermore, we introduce DVCD, a novel dataset for building change detection from UAV viewpoints. Experiments on four widely-used datasets demonstrate significant improvements over existing method The code and pre-trained models are available in {https://github.com/Yu-Zhouz/SegChange-R1}.