{"ID":2865048,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.21894","arxiv_id":"2509.21894","title":"LG-CD: Enhancing Language-Guided Change Detection through SAM2 Adaptation","abstract":"Remote Sensing Change Detection (RSCD) typically identifies changes in land cover or surface conditions by analyzing multi-temporal images. Currently, most deep learning-based methods primarily focus on learning unimodal visual information, while neglecting the rich semantic information provided by multimodal data such as text. To address this limitation, we propose a novel Language-Guided Change Detection model (LG-CD). This model leverages natural language prompts to direct the network's attention to regions of interest, significantly improving the accuracy and robustness of change detection. Specifically, LG-CD utilizes a visual foundational model (SAM2) as a feature extractor to capture multi-scale pyramid features from high-resolution to low-resolution across bi-temporal remote sensing images. Subsequently, multi-layer adapters are employed to fine-tune the model for downstream tasks, ensuring its effectiveness in remote sensing change detection. Additionally, we design a Text Fusion Attention Module (TFAM) to align visual and textual information, enabling the model to focus on target change regions using text prompts. Finally, a Vision-Semantic Fusion Decoder (V-SFD) is implemented, which deeply integrates visual and semantic information through a cross-attention mechanism to produce highly accurate change detection masks. Our experiments on three datasets (LEVIR-CD, WHU-CD, and SYSU-CD) demonstrate that LG-CD consistently outperforms state-of-the-art change detection methods. Furthermore, our approach provides new insights into achieving generalized change detection by leveraging multimodal information.","short_abstract":"Remote Sensing Change Detection (RSCD) typically identifies changes in land cover or surface conditions by analyzing multi-temporal images. Currently, most deep learning-based methods primarily focus on learning unimodal visual information, while neglecting the rich semantic information provided by multimodal data such...","url_abs":"https://arxiv.org/abs/2509.21894","url_pdf":"https://arxiv.org/pdf/2509.21894v1","authors":"[\"Yixiao Liu\",\"Yizhou Yang\",\"Jinwen Li\",\"Jun Tao\",\"Ruoyu Li\",\"Xiangkun Wang\",\"Min Zhu\",\"Junlong Cheng\"]","published":"2025-09-26T05:30:11Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}