期刊
IEEE GEOSCIENCE AND REMOTE SENSING MAGAZINE
卷 11, 期 3, 页码 98-106出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/MGRS.2023.3281651
关键词
Earth; Scene classification; Spaceborne radar; Source coding; Semantic segmentation; Self-supervised learning; Benchmark testing
This article introduces an unlabeled dataset SSL4EO-S12 for self-supervised pretraining of Earth observation satellite imagery. The authors demonstrate the effectiveness of SSL4EO-S12 in representative methods and multiple applications, and compare it with existing datasets.
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 Self-Supervised Learning for Earth Observation-Sentinel-1/2 (SSL4EO-S12) 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 https://github.com/zhu-xlab/SSL4EO-S12.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据