论文标题
在数据稀缺下，微调分割模型到危机领域的微调分割模型的采样策略
Sampling Strategy for Fine-Tuning Segmentation Models to Crisis Area under Scarcity of Data
论文作者
论文摘要
在人道主义危机响应任务中使用遥感在人道主义危机中，已经建立了良好的事实，并反复证明是相关的。问题之一是要获得金色注释，因为它是昂贵且耗时的，这几乎无法将模型调整到受危机影响的新区域。在时间至关重要的地方，资源是有限的，环境正在不断变化，模型必须发展并提供灵活的方法来适应新情况。我们要回答的问题是，在带注释的数据稀缺下，样本的优先级在微调和其他经典抽样方法中提供了更好的结果？我们提出了一种基于估计的模型和样本属性（如预测的评分），在微调过程中指导数据收集的方法。我们提出了两个用于计算样本优先级的公式。我们的方法将技术从可解释性，表示学习和积极学习中融合在一起。我们已经将方法应用于深度学习模型，以进行语义细分U -NET，在建筑物检测的遥感应用中，这是人道主义应用中遥感的核心用例之一。初步结果显示了在数据条件稀缺下调整语义分割模型的样品优先级的实用性。
The use of remote sensing in humanitarian crisis response missions is well-established and has proven relevant repeatedly. One of the problems is obtaining gold annotations as it is costly and time consuming which makes it almost impossible to fine-tune models to new regions affected by the crisis. Where time is critical, resources are limited and environment is constantly changing, models has to evolve and provide flexible ways to adapt to a new situation. The question that we want to answer is if prioritization of samples provide better results in fine-tuning vs other classical sampling methods under annotated data scarcity? We propose a method to guide data collection during fine-tuning, based on estimated model and sample properties, like predicted IOU score. We propose two formulas for calculating sample priority. Our approach blends techniques from interpretability, representation learning and active learning. We have applied our method to a deep learning model for semantic segmentation, U-Net, in a remote sensing application of building detection - one of the core use cases of remote sensing in humanitarian applications. Preliminary results shows utility in prioritization of samples for tuning semantic segmentation models under scarcity of data condition.
