对比多种模型与微调方法，提升卫星图像滑坡检测精度。
A Benchmark Study of Segmentation Models and Adaptation Strategies for Landslide Detection from Satellite Imagery
- 系统评测CNN、Transformer及大模型在滑坡检测中的表现。
- 基于GDCLD数据集，变压器模型性能最优，参数高效微调可降95%参数。
- 适合遥感、灾害监测领域研究者参考，关注模型效率与泛化能力。
从高分辨率卫星影像中检测滑坡是灾害响应与风险评估的关键任务，但当前主流分割架构与微调策略在此任务上的相对有效性仍不明确。本文对卷积神经网络、基于Transformer的分割模型以及大规模预训练基础模型进行了系统性基准测试。基于全球分布的同震滑坡数据集（GDCLD），在统一训练与评估协议下，比较了代表性模型的表现，并对比了全量微调与参数高效微调方法（如LoRA和AdaLoRA）的性能-效率权衡。实验结果表明，基于Transformer的模型实现优异分割性能，而参数高效微调方法可将可训练参数减少高达95%，同时保持与全量微调相当的精度。此外，通过对比验证集与保留测试集的表现，分析了模型在分布偏移下的泛化能力。
原文摘要 · Abstract (English)
Landslide detection from high resolution satellite imagery is a critical task for disaster response and risk assessment, yet the relative effectiveness of modern segmentation architectures and finetuning strategies for this problem remains insufficiently understood. In this work, we present a systematic benchmarking study of convolutional neural networks, transformer based segmentation models, and large pre-trained foundation models for landslide detection. Using the Globally Distributed Coseismic Landslide Dataset (GDCLD) dataset, we evaluate representative CNN- and transformer-based segmentation models alongside large pretrained foundation models under consistent training and evaluation protocols. In addition, we compare full fine-tuning with parameter-efficient fine-tuning methods, including LoRA and AdaLoRA, to assess their performance efficiency tradeoffs. Experimental results show that transformer-based models achieve strong segmentation performance, while parameter efficient finetuning reduces trainable parameters by up to 95% with comparable accuracy to full finetuning. We further analyze generalization under distribution shift by comparing validation and held-out test performance.
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。