Efficient landslide mapping is crucial for disaster mitigation and relief. Recently, deep learning methods have shown promising results in landslide mapping using satellite imagery. However, the sample sparsity and geographic diversity of landslides have challenged the transferability of deep learning models. In this paper, we proposed a universal adapter module that can be seamlessly embedded into existing segmentation models for transferable landslide mapping. The adapter can achieve high-accuracy cross-regional landslide segmentation with a small sample set, requiring minimal parameter adjustments. In detail, the pre-trained baseline model freezes its parameters to keep learned knowledge of the source domain, while the lightweight adapter fine-tunes only a few parameters to learn new landslide features of the target domain. Structurally, we introduced an attention mechanism to enhance the feature extraction of the adapter. To validate the proposed adapter module, 4321 landslide samples were prepared, and the Segment Anything Model (SAM) and other baseline models, along with four transfer strategies were selected for controlled experiments. In addition, Sentinel-2 satellite imagery in the Himalayas and Hengduan Mountains, located on the southern and southeastern edges of the Tibetan Plateau was collected for evaluation. The controlled experiments reported that SAM, when combined with our adapter module, achieved a peak mean Intersection over Union (mIoU) of 82.3 %. For other baseline models, integrating the adapter improved mIoU by 2.6 % to 12.9 % compared with traditional strategies on cross-regional landslide mapping. In particular, baseline models with Transformers are more suitable for fine-tuning parameters. Furthermore, the visualized feature maps revealed that fine-tuning shallow encoders can achieve better effects in model transfer. Besides, the proposed adapter can effectively extract landslide features and focus on specific spatial and channel domains with significant features. We also quantified the spectral, scale, and shape features of landslides and analyzed their impacts on segmentation results. Our analysis indicated that weak spectral differences, as well as extreme scale and edge shapes are detrimental to the accuracy of landslide segmentation. Overall, this adapter module provides a new perspective for large-scale transferable landslide mapping.

中文翻译：

---

用于可转移滑坡测绘的分割模型中的通用适配器


高效的滑坡测绘对于减灾和救灾至关重要。最近，深度学习方法在使用卫星图像的滑坡制图方面显示出有希望的结果。然而，滑坡的样本稀疏性和地理多样性对深度学习模型的可迁移性提出了挑战。在本文中，我们提出了一个通用适配器模块，该模块可以无缝嵌入到现有的分割模型中，用于可转移的滑坡测绘。该适配器可以用小样本集实现高精度的跨区域滑坡分割，需要最少的参数调整。具体来说，预先训练的基线模型冻结了其参数，以保持对源域的学习知识，而轻量级适配器只微调了几个参数，以学习目标域的新滑坡特征。在结构上，我们引入了一种注意力机制来增强适配器的特征提取。为了验证所提出的适配器模块，准备了 4321 个滑坡样本，并选择了 Segment Anything Model （SAM） 和其他基线模型以及四种转移策略进行对照实验。此外，还收集了位于青藏高原南部和东南边缘的喜马拉雅山和横断山脉的 Sentinel-2 卫星图像进行评估。对照实验报告称，当 SAM 与我们的适配器模块结合使用时，峰值平均交并比 （mIoU） 为 82.3 %。对于其他基线模型，与传统的跨区域滑坡测绘策略相比，集成适配器将 mIoU 提高了 2.6% 至 12.9%。特别是，带有 Transformer 的基线模型更适合微调参数。 此外，可视化特征图表明，微调浅编码器可以在模型迁移中取得更好的效果。此外，所提出的适配器可以有效地提取滑坡特征，并专注于具有显著特征的特定空间域和通道域。我们还量化了滑坡的光谱、规模和形状特征，并分析了它们对分割结果的影响。我们的分析表明，弱光谱差异以及极端的尺度和边缘形状对滑坡分割的准确性是有害的。总的来说，这个适配器模块为大规模可移动的滑坡测绘提供了新的视角。