Seeing the bigger picture: Enabling large context windows in neural networks by combining multiple zoom levels

Abstract

When adopting deep learning methods for remote sensing applications, the data usually needs to be cut into patches due to hardware limitations. Clearly, this practice discards a lot of contextual information as the model's information is limited to imagery from the given patch. We propose a memory-efficient way around this limitation by using multiple patches of varying spatial extents on different resolution levels. Finally, this new approach is evaluated for the task of automated sea ice charting, where the added contextual information is shown to be beneficial to model performance.