Multi-Scale and Temporal Transfer Learning for Automatic Tracking of Internal Ice Layers
Multi-Scale and Temporal Transfer Learning for Automatic Tracking of Internal Ice Layers
复制标题
DOI：
10.1109/igarss39084.2020.9323758
复制
发表时间：
2020-09
期刊：
影响因子：
--
通讯作者：
M. Yari;M. Rahnemoonfar;J. Paden
中科院分区：
文献类型：
--
作者：
M. Yari;M. Rahnemoonfar;J. Paden
近年来，实用的深度学习技术极大地影响了我们的数据分析方法。然而，在许多实际问题中，即使有大量数据集可用，深度学习方法也不太成功，这是因为缺乏大量有标记的数据集、存在噪声或数据缺失。在这项工作中，我们的目标是追踪不同年份由各种传感器收集的雷达图像中的内部冰层。我们将表明迁移学习通常效果不佳。然而，如果深度学习模型在有噪声的图像上进行训练，将会有显著的改进。与空间迁移学习不同，我们的实验表明时间迁移学习能够提供好得多的结果。
Pragmatic Deep Learning techniques in recent years have greatly influenced our approaches to data analysis. However, in many real-world problems, even when a large dataset is available, Deep Learning methods have shown less success, for the lack of large labeled dataset, presence of noise, or missing data. In this work, our goal is to track internal ice layers in radar images gathered with various sensors in different years. We will show that transfer learning will not generally work well. However, if the Deep Learning model gets trained on noisy images, there would be a significant improvement. Unlike spatial Transfer Learning, our experiments show that temporal Transfer Learning can provide considerably better results.