用自监督学习提升遥感图像表征，性能超越主流方法。
SatDINO: A Deep Dive into Self-Supervised Pretraining for Remote Sensing
- 基于DINO框架构建专用于卫星图像的自监督预训练模型
- 在多个数据集上表现优于主流掩码自编码器方法，精度领先1.5-3.2%
- 提出地距编码与动态视图采样等可独立使用的改进技术
自监督学习在遥感领域展现出巨大潜力，因其可利用海量未标注数据。本文深入研究了对比型自监督方法DINO在遥感图像预训练中的应用，提出专为卫星影像设计的SatDINO模型。通过在多个数据集上的多组测试验证，SatDINO显著优于基于掩码自编码器（MAE）的主流方法，在多个基准测试中达到竞争性水平。我们还进行了严格的消融实验，评估模型各组件的作用。最后，提出了若干新改进，如新的地面采样距离（GSD）编码方式和自适应视图采样策略，这些改进可独立应用于我们的SatDINO模型。代码与训练模型已开源：https://github.com/strakaj/SatDINO。
原文摘要 · Abstract (English)
Self-supervised learning has emerged as a powerful tool for remote sensing, where large amounts of unlabeled data are available. In this work, we investigate the use of DINO, a contrastive self-supervised method, for pretraining on remote sensing imagery. We introduce SatDINO, a model tailored for representation learning in satellite imagery. Through extensive experiments on multiple datasets in multiple testing setups, we demonstrate that SatDINO outperforms other state-of-the-art methods based on much more common masked autoencoders (MAE) and achieves competitive results in multiple benchmarks. We also provide a rigorous ablation study evaluating SatDINO's individual components. Finally, we propose a few novel enhancements, such as a new way to incorporate ground sample distance (GSD) encoding and adaptive view sampling. These enhancements can be used independently on our SatDINO model. Our code and trained models are available at: https://github.com/strakaj/SatDINO.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。