Land Use Prediction using Electro-Optical to SAR Few-Shot Transfer Learning
This work addresses land use monitoring for environmental and urban planning applications, but it is incremental as it builds on existing distributional alignment methods with practical extensions.
The paper tackled land use prediction by developing a few-shot transfer learning method from electro-optical to synthetic aperture radar satellite imagery, showing that it outperforms common baselines on datasets with many classes.
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.