SegChange-R1:Augmented Reasoning for Remote Sensing Change Detection via Large Language Models

2025-06-22

AI Summary

To address misalignment of cross-temporal features, low detection accuracy, and slow convergence in remote sensing change detection, this paper proposes a large language model (LLM)-driven reasoning-enhanced framework. Specifically, textual descriptions guide the model to attend to salient change regions; a linear-attention-based bird’s-eye view (BEV) spatial transformation module is designed to align multi-temporal visual features and enhance semantic consistency; and we introduce DVCD—the first drone-view building change detection dataset. Experiments demonstrate that our method achieves significant improvements over state-of-the-art approaches across four mainstream benchmarks, simultaneously boosting both detection accuracy and training convergence speed. All code, pre-trained models, and the DVCD dataset are publicly released.

Technology Category

• Computer Vision: Large Vision Models
• Machine Learning: Large Multimodal Models (LMMs)
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Large language models for search
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Remote sensing change detection is widely used in a variety of fields such as urban planning, terrain and geomorphology analysis, and environmental monitoring, mainly by analyzing the significant change differences of features (e.g., building changes) in the same spatial region at different time phases. 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 aims at guiding the model to segment the more interested change regions, thus accelerating the convergence speed. Moreover, we design a spatial transformation module (BEV) based on linear attention, which solves the problem of modal misalignment in change detection by unifying features from different temporal perspectives onto the BEV space. In addition, we construct the first dataset for building change detection from UAV viewpoints (DVCD ), and our experiments on four widely-used change detection datasets show a significant improvement over existing methods. The code and pre-trained models are available in https://github.com/Yu-Zhouz/SegChange-R1.

Problem

• Enhancing change detection accuracy using LLM-augmented reasoning
• Solving modal misalignment via spatial transformation module
• Improving building change detection from UAV viewpoints

Innovation

• LLM-augmented inference for enhanced change detection
• Linear attention-based BEV for modal alignment
• First UAV-view building change detection dataset