通过专家协作提升卫星图像跨域泛化能力
CoDEx: Combining Domain Expertise for Spatial Generalization in Satellite Image Analysis
- 为每个领域训练专用模型，再通过相似性学习统一专家预测
- 在4个数据集上均优于现有域泛化与自适应方法
- 适合需要跨区域卫星图像分析的研究者
全球地形差异导致卫星图像分析模型在测试时性能下降，即使使用大规模全球数据集仍存在此问题。为此，我们提出一种新型卫星图像域泛化框架。不追求单一通用模型，而是为每个训练域训练一个专家模型，并学习专家间的相似性，促使相似专家保持一致。测试时，模型选择模块识别最适配的专家并聚合其预测结果。在DynamicEarthNet、MUDS、OSCD和FMoW四个数据集上的实验表明，该方法持续优于现有的域泛化与自适应方法。代码已公开于https://github.com/Abhishek19009/CoDEx。
原文摘要 · Abstract (English)
Global variations in terrain appearance raise a major challenge for satellite image analysis, leading to poor model performance when training on locations that differ from those encountered at test time. This remains true even with recent large global datasets. To address this challenge, we propose a novel domain-generalization framework for satellite images. Instead of trying to learn a single generalizable model, we train one expert model per training domain, while learning experts' similarity and encouraging similar experts to be consistent. A model selection module then identifies the most suitable experts for a given test sample and aggregates their predictions. Experiments on four datasets (DynamicEarthNet, MUDS, OSCD, and FMoW) demonstrate consistent gains over existing domain generalization and adaptation methods. Our code is publicly available at https://github.com/Abhishek19009/CoDEx.
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。