Evaluation of Season Invariant Self-Supervised Representations on Remote Sensing Land Cover Data

Training current deep neural network architectures for automated earth remote sensing raises the necessity of huge amounts of labeled data or the application of suitable transfer learning approaches. Unfortunately, transfer learning representations learned on ImageNet are not well suited for the remote sensing domain. Fortunately, self-supervised learning (SSL) is stepping in to fill this gap, by providing domain specific representations without the need for labels. Moreover, in contrast to natural scenes, earth’s land cover classes change with seasons, which has to be considered during training and data collection. Luckily, unlabeled observations over different seasons at the same location are easy to come by, with a lot of publicly available data from, e.g., the Sentinel-2 mission and automated sampling approaches.