Spatial Knowledge-Infused Hierarchical Learning: An Application in Flood Mapping on Earth Imagery
Spatial Knowledge-Infused Hierarchical Learning: An Application in Flood Mapping on Earth Imagery
复制标题
DOI：
10.1145/3589132.3625591
复制
发表时间：
2023-11
期刊：
影响因子：
--
通讯作者：
Zelin Xu;Tingsong Xiao;Wenchong He;Yu Wang;Zhe Jiang
中科院分区：
文献类型：
--
作者：
Zelin Xu;Tingsong Xiao;Wenchong He;Yu Wang;Zhe Jiang
地球图像的深度学习在农业，生态学和自然灾害管理等地球科学应用中起着越来越重要的作用。尽管如此，有限的培训标签通常会阻碍进度。鉴于训练标签有限的地球图像，基础深神网络模型以及具有标签约束的空间知识基础，我们的问题是在训练神经网络时推断完整的标签。由于稀疏和嘈杂的输入标签，标签推理过程中的空间不确定性以及与大量样本位置相关的高计算成本，因此该问题具有挑战性。关于神经符号模型的现有作品着重于将符号逻辑整合到神经网络（例如，损失功能，模型架构和培训标签增强）中，但是这些方法并未完全解决空间数据的挑战（例如，空间不确定，贸易，交易，交易 - 空间粒度和计算成本之间的犯规）。为了弥合这一差距，我们提出了一个新型的空间知识融合的层次学习（SKI-HL）框架，该框架在多分辨率层次结构中迭代地占据样品标签。我们的框架由一个模块组成，可以根据空间不确定性选择性地推断出不同的分辨率和一个模块，以训练具有不确定性意识的多个实体学习的神经网络参数。对现实世界洪水映射数据集的广泛实验表明，所提出的模型的表现优于几种基线方法。该代码可在https://github.com/zelinxu2000/ski-hl上找到。
Deep learning for Earth imagery plays an increasingly important role in geoscience applications such as agriculture, ecology, and natural disaster management. Still, progress is often hindered by the limited training labels. Given Earth imagery with limited training labels, a base deep neural network model, and a spatial knowledge base with label constraints, our problem is to infer the full labels while training the neural network. The problem is challenging due to the sparse and noisy input labels, spatial uncertainty within the label inference process, and high computational costs associated with a large number of sample locations. Existing works on neuro-symbolic models focus on integrating symbolic logic into neural networks (e.g., loss function, model architecture, and training label augmentation), but these methods do not fully address the challenges of spatial data (e.g., spatial uncertainty, the trade-off between spatial granularity and computational costs). To bridge this gap, we propose a novel Spatial Knowledge-Infused Hierarchical Learning (SKI-HL) framework that iteratively infers sample labels within a multi-resolution hierarchy. Our framework consists of a module to selectively infer labels in different resolutions based on spatial uncertainty and a module to train neural network parameters with uncertainty-aware multi-instance learning. Extensive experiments on real-world flood mapping datasets show that the proposed model outperforms several baseline methods. The code is available at https://github.com/ZelinXu2000/SKI-HL.