Abstract
We propose a vision transformer (ViT)-based deep learning framework to refine disaster-affected area segmentation from remote sensing imagery, aiming to support and enhance the Emergent Value Added Product (EVAP) developed by the Taiwan Space Agency (TASA). The process starts with a small set of manually annotated regions. We then apply principal component analysis (PCA)-based feature space analysis and construct a confidence index (CI) to expand these labels, producing a weakly supervised training set. These expanded labels are then used to train ViT-based encoder-decoder models with multi-band inputs from Sentinel-2 and Formosat-5 imagery. Our architecture supports multiple decoder variants and multi-stage loss strategies to improve performance under limited supervision. During the evaluation, model predictions are compared with higher-resolution EVAP output to assess spatial coherence and segmentation consistency. Case studies on the 2022 Poyang Lake drought and the 2023 Rhodes wildfire demonstrate that our framework improves the smoothness and reliability of segmentation results, offering a scalable approach for disaster mapping when accurate ground truth is unavailable.
Abstract (translated)
我们提出了一种基于视觉变换器（ViT）的深度学习框架，旨在通过遥感图像来优化受灾地区分割，以支持并提升台湾太空机构（TASA）开发的紧急增值产品（EVAP）。该过程从一小部分手动标注区域开始。然后应用基于主成分分析（PCA）的特征空间分析，并构建置信指数（CI），以此扩大这些标签，生成一个弱监督训练集。接着使用扩展后的标签来训练多频段输入来自Sentinel-2和Formosat-5图像的ViT编码器-解码器模型。 我们的架构支持多种解码器变体和多阶段损失策略，在有限监督下提高性能。在评估过程中，将模型预测与高分辨率EVAP输出进行比较，以评估空间一致性及分割的一致性。2022年鄱阳湖干旱以及2023年罗德岛野火的案例研究表明，我们的框架提高了分割结果的平滑度和可靠性，在缺乏准确地面真实情况的情况下为灾害制图提供了一种可扩展的方法。
URL
https://arxiv.org/abs/2507.16849
