构建火星滑坡检测多模态数据集，助力遥感图像自动识别
MMLSv2: A Multimodal Dataset for Martian Landslide Detection in Remote Sensing Imagery
- 融合七种波段影像，含高程、坡度等多维度信息
- 包含664张训练验证图像和276张跨区域测试图
- 可评估模型在陌生区域的泛化能力，推动鲁棒性研究
我们提出MMLSv2，一个用于火星表面滑坡分割的多模态数据集。该数据集包含七种波段的遥感影像：可见光三通道（RGB）、数字高程模型（DEM）、坡度、热惯性及灰度图像。数据集共包含664张图像，按训练、验证和测试集划分。此外，还发布了276张来自地理上不重叠区域的独立测试集，用于评估模型的空间泛化能力。多种分割模型的实验表明，该数据集支持稳定训练并达到具有竞争力的性能，但在破碎、细长及小尺度滑坡区域仍存在挑战。在独立测试集上的评估显示性能显著下降，凸显其对模型鲁棒性和外分布泛化能力评估的重要价值。数据集将公开于：https://github.com/MAIN-Lab/MMLS_v2
原文摘要 · Abstract (English)
We present MMLSv2, a dataset for landslide segmentation on Martian surfaces. MMLSv2 consists of multimodal imagery with seven bands: RGB, digital elevation model, slope, thermal inertia, and grayscale channels. MMLSv2 comprises 664 images distributed across training, validation, and test splits. In addition, an isolated test set of 276 images from a geographically disjoint region from the base dataset is released to evaluate spatial generalization. Experiments conducted with multiple segmentation models show that the dataset supports stable training and achieves competitive performance, while still posing challenges in fragmented, elongated, and small-scale landslide regions. Evaluation on the isolated test set leads to a noticeable performance drop, indicating increased difficulty and highlighting its value for assessing model robustness and generalization beyond standard in-distribution settings. Dataset will be available at: https://github.com/MAIN-Lab/MMLS_v2
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。