LandslideFM：迈向统一滑坡感知与理解的基础模型
LandslideFM: A Foundation Model Towards Unified Landslide Perception and Understanding
AI 导读
研究者提出 LandslideFM，首个将视觉感知任务与滑坡语境解读相连接的统一基础模型。它通过 Source-Agreement Graduated Trust 半监督学习框架适配多视觉任务，并将预测的滑坡区域作为空间引导输入经参数高效微调的视觉语言模型，实现滑坡推理分析。
正文 · 原文
Abstract:Intelligent landslide detection is essential for disaster prevention. However, existing models primarily focus on isolated visual tasks, require extensive labeled data, and lack deep analytical and scene-understanding capabilities. To address these limitations, we propose LandslideFM, the first unified foundation model that connects visual perception tasks with contextual interpretation of landslides. Specifically, LandslideFM adapts to multiple visual tasks via a Source-Agreement Graduated Trust semi-supervised learning framework that leverages limited labeled data alongside abundant unlabeled data. Furthermore, predicted landslide regions provide explicit spatial guidance to a Vision-Language Model adapted through parameter-efficient fine-tuning, enabling comprehensive landslide reasoning. To support training and evaluation in this domain, we also present LandslideVL, the first benchmark for intelligent landslide analysis, combining visual imagery and newly introduced textual prompts. Comprehensive experiments across public datasets and LandslideVL demonstrate that LandslideFM achieves superior quantitative and qualitative performance. Most importantly, LandslideFM surpasses general-purpose VLMs in specialized landslide reasoning and scene analysis. Our code is released at this https URL.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.12936 [cs.AI] |
| (or arXiv:2611.12936v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.12936 arXiv-issued DOI via DataCite |
Submission history
From: Shanwen Wang [view email]
[v1]
Fri, 6 Nov 2026 12:59:06 UTC (38,635 KB)
来源：arXiv cs.AI · arxiv.org