DINO-MC: Self-supervised Contrastive Learning for Remote Sensing Imagery with Multi-sized Local Crops

Due to the costly nature of remote sensing image labeling and the large volume of available unlabeled imagery, self-supervised methods that can learn feature representations without manual annotation have received great attention. While prior works have explored self-supervised learning in remote sensing tasks, pretext tasks based on local-global view alignment remain underexplored. Inspired by DINO, which employs an effective representation learning structure with knowledge distillation based on global-local view alignment, we formulate two pretext tasks for use in self-supervised learning on remote sensing imagery (SSLRS). Using these tasks, we explore the effectiveness of positive temporal contrast as well as multi-sized views on SSLRS. Moreover, we extend DINO and propose DINO-MC which uses local views of various sized crops instead of a single fixed size. Our experiments demonstrate that even when pre-trained on only 10% of the dataset, DINO-MC performs on par or better than existing state of the art SSLRS methods on multiple remote sensing tasks, while using less computational resources. All codes, models and results are available at https://github.com/WennyXY/DINO-MC.