论文标题
使用电光到SAR几次转移学习的土地使用预测
Land Use Prediction using Electro-Optical to SAR Few-Shot Transfer Learning
论文作者
论文摘要
卫星图像分析对土地使用，城市化和生态系统监测具有重要意义。深度学习方法可以通过支持模态之间的知识转移以补偿各个缺点，从而促进分析不同卫星形态的分析，例如电光（EO）和合成孔径雷达（SAR）图像。最近的进步表明，神经网络嵌入的分布比对如何通过采用切片的瓦斯坦距离（SWD）损失来产生强大的转移学习模型。我们分析了如何将该方法应用于Sentinel -1和-2卫星图像，并开发出几种扩展以使其在实践中有效。在对少数射击本地气候区域（LCZ）预测的应用程序中，我们表明这些网络在数据集上的表现优于具有大量类的数据集。此外，我们提供的证据表明，实例归一化可以显着稳定训练过程，并且使用监督的对比度学习明确地塑造嵌入空间可以改善性能。
Satellite image analysis has important implications for land use, urbanization, and ecosystem monitoring. Deep learning methods can facilitate the analysis of different satellite modalities, such as electro-optical (EO) and synthetic aperture radar (SAR) imagery, by supporting knowledge transfer between the modalities to compensate for individual shortcomings. Recent progress has shown how distributional alignment of neural network embeddings can produce powerful transfer learning models by employing a sliced Wasserstein distance (SWD) loss. We analyze how this method can be applied to Sentinel-1 and -2 satellite imagery and develop several extensions toward making it effective in practice. In an application to few-shot Local Climate Zone (LCZ) prediction, we show that these networks outperform multiple common baselines on datasets with a large number of classes. Further, we provide evidence that instance normalization can significantly stabilize the training process and that explicitly shaping the embedding space using supervised contrastive learning can lead to improved performance.
