SSL4EO-S12: A large-scale multimodal, multitemporal dataset for self-supervised learning in Earth observation [Software and Data Sets]
Yi Wang, Nassim Ait Ali Braham, Zhitong Xiong, Chenying Liu, Conrad M Albrecht, Xiao Xiang Zhu
Abstract
Self-supervised pretraining bears the potential to generate expressive representations from large-scale Earth observation (EO) data without human annotation. However, most existing pretraining in the field is based on ImageNet or medium-sized, labeled remote sensing (RS) datasets. In this article, we share an unlabeled dataset <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Self-Supervised Learning for Earth Observation-Sentinel-1/2</i> ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">SSL4EO</i> - <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">S12</i> ) to assemble a large-scale, global, multimodal, and multiseasonal corpus of satellite imagery. We demonstrate SSL4EO-S12 to succeed in self-supervised pretraining for a set of representative methods: momentum contrast (MoCo), self-distillation with no labels (DINO), masked autoencoders (MAE), and data2vec, and multiple downstream applications, including scene classification, semantic segmentation, and change detection. Our benchmark results prove the effectiveness of SSL4EO-S12 compared to existing datasets. The dataset, related source code, and pretrained models are available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/zhu-xlab/SSL4EO-S12</uri> .