In-domain representation learning for remote sensing
It addresses a domain-specific problem for remote sensing researchers by creating a common evaluation protocol and baselines, but it is incremental as it builds on existing methods.
The paper tackled the lack of representation learning focus in remote sensing by providing standardized access to 5 diverse datasets and establishing baselines, achieving state-of-the-art performance on these datasets.
Given the importance of remote sensing, surprisingly little attention has been paid to it by the representation learning community. To address it and to establish baselines and a common evaluation protocol in this domain, we provide simplified access to 5 diverse remote sensing datasets in a standardized form. Specifically, we investigate in-domain representation learning to develop generic remote sensing representations and explore which characteristics are important for a dataset to be a good source for remote sensing representation learning. The established baselines achieve state-of-the-art performance on these datasets.