面向卫星图像洪灾后建筑损毁评估的注意力机制与一致性正则化半监督学习基准测试
Benchmarking Attention Mechanisms and Consistency Regularization Semi-Supervised Learning for Post-Flood Building Damage Assessment in Satellite Images
AI总结：
本文针对洪灾后建筑损毁评估任务与变化检测的差异，提出SPAUNet模型增强细微变化识别能力，构建多种半监督一致性正则化策略，在xBD数据集上取得优于现有变化检测方法的效果，建立了该任务的新基准。
摘要：
洪灾后建筑损毁评估对应急响应和灾后重建规划至关重要。当前研究在神经网络设计中未考虑灾害评估（DA）与变化检测（CD）的不同需求。本文聚焦两类关键差异：1）DA卫星图像中的建筑变化特征比CD中的更细微；2）DA数据集面临更严重的数据稀缺和标签不平衡问题。为解决这些问题，在模型架构方面，研究探索了注意力机制在洪灾后DA任务中的基准性能，并提出Simple Prior Attention UNet（SPAUNet，简单先验注意力UNet）以增强模型识别细微变化的能力；在半监督学习（SSL）策略方面，本文构建了四种不同的图像级标签类别参考分布组合用于一致性训练。在xBD数据集的洪水事件上的实验结果表明，SPAUNet在监督学习实验中表现优异，损毁分类的召回率达到79.10%，F1分数达到71.32%，优于CD方法。结果表明了面向DA任务设计模型的必要性。SSL实验证明了图像级一致性正则化对模型的积极作用。使用伪标签构建一致性训练的参考分布取得了最佳效果，证明了利用大量未标记数据的类别分布进行SSL的潜力。本文阐明了DA与CD任务的差异，初步探索了利用先验注意力机制和图像级一致性正则化的模型设计策略，建立了新的洪灾后DA任务基准方法。
英文摘要：
Post-flood building damage assessment is critical for rapid response and post-disaster reconstruction planning. Current research fails to consider the distinct requirements of disaster assessment (DA) from change detection (CD) in neural network design. This paper focuses on two key differences: 1) building change features in DA satellite images are more subtle than in CD; 2) DA datasets face more severe data scarcity and label imbalance. To address these issues, in terms of model architecture, the research explores the benchmark performance of attention mechanisms in post-flood DA tasks and introduces Simple Prior Attention UNet (SPAUNet) to enhance the model's ability to recognize subtle changes, in terms of semi-supervised learning (SSL) strategies, the paper constructs four different combinations of image-level label category reference distributions for consistent training. Experimental results on flood events of xBD dataset show that SPAUNet performs exceptionally well in supervised learning experiments, achieving a recall of 79.10% and an F1 score of 71.32% for damaged classification, outperforming CD methods. The results indicate the necessity of DA task-oriented model design. SSL experiments demonstrate the positive impact of image-level consistency regularization on the model. Using pseudo-labels to form the reference distribution for consistency training yields the best results, proving the potential of using the category distribution of a large amount of unlabeled data for SSL. This paper clarifies the differences between DA and CD tasks. It preliminarily explores model design strategies utilizing prior attention mechanisms and image-level consistency regularization, establishing new post-flood DA task benchmark methods.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
