论文标题
使用卫星图像中的对象检测生成可解释的贫困图
Generating Interpretable Poverty Maps using Object Detection in Satellite Images
论文作者
论文摘要
对于政府和人道主义组织来说，准确的地方贫困衡量是追踪改善生计和分配稀缺资源的进步的必不可少的任务。使用卫星图像预测贫困的最新计算机视觉进展显示出越来越高的准确性，但它们不能产生对决策者解释的特征，从而抑制了从业者的采用。在这里，我们演示了一个可解释的计算框架，可以通过将对象检测器应用于高分辨率（30厘米）卫星图像来准确预测地方一级的贫困。使用对象的加权计数作为特征，我们在预测乌干达的村庄贫困方面达到了0.539 Pearson的R^2，比现有（且易于解释的）基准提高了31％。特征重要性和消融分析揭示了对象数量和贫困预测之间的直观关系。我们的结果表明，至少在这个重要领域，可解释性不必以绩效为代价。
Accurate local-level poverty measurement is an essential task for governments and humanitarian organizations to track the progress towards improving livelihoods and distribute scarce resources. Recent computer vision advances in using satellite imagery to predict poverty have shown increasing accuracy, but they do not generate features that are interpretable to policymakers, inhibiting adoption by practitioners. Here we demonstrate an interpretable computational framework to accurately predict poverty at a local level by applying object detectors to high resolution (30cm) satellite images. Using the weighted counts of objects as features, we achieve 0.539 Pearson's r^2 in predicting village-level poverty in Uganda, a 31% improvement over existing (and less interpretable) benchmarks. Feature importance and ablation analysis reveal intuitive relationships between object counts and poverty predictions. Our results suggest that interpretability does not have to come at the cost of performance, at least in this important domain.
