Global land cover (GLC) products can be utilized to provide geographical supervision for remote sensing representation learning, which has significantly improved downstream tasks’ performance and decreased the demand of manual annotations. However, the time differences between remote sensing images and GLC products may introduce deviations in geographical supervision. In this article, we propose a geographical supervision correction (GeCo) method for remote sensing representation learning. Deviated geographical supervision generated by GLC products can be corrected adaptively using the correction matrix during network pretraining and joint optimization process is designed to simultaneously update the correction matrix and network parameters. In addition, we identify prior knowledge on geographical supervision to guide representation learning and restrict the correction process. The prior knowledge named “minor changes” implies that the geographical supervision may not change significantly, whereas the prior knowledge named “spatial aggregation” implies that land covers are aggregated in their spatial distribution. According to the prior knowledge, corresponding regularization terms are proposed to prevent abrupt changes in the geographical supervision correction process and excessive smoothing of network outputs, thereby ensuring the adaptive correction process’s correctness. Experimental results demonstrate that our proposed method outperforms random initialization, ImageNet pretraining, and other representation learning methods on a variety of downstream tasks. In particular, when compared to the method that learns representations directly from deviated geographical supervision, it is proven that our method can eliminate the influence of deviations and further improve the effect of representation learning.

中文翻译：

---

遥感表征学习的地理监督校正


全球土地覆盖（GLC）产品可用于为遥感表示学习提供地理监督，这显着提高了下游任务的性能并减少了手动注释的需求。然而，遥感影像与GLC产品之间的时间差异可能会带来地理监管的偏差。在本文中，我们提出了一种用于遥感表示学习的地理监督校正（GeCo）方法。 GLC产品产生的地理监督偏差可以在网络预训练期间使用校正矩阵进行自适应校正，联合优化过程被设计为同时更新校正矩阵和网络参数。此外，我们确定地理监督的先验知识来指导表示学习并限制纠正过程。称为“微小变化”的先验知识意味着地理监管可能不会发生重大变化，而称为“空间聚合”的先验知识意味着土地覆盖在空间分布上是聚合的。根据先验知识，提出相应的正则化项，防止地理监督校正过程的突变和网络输出的过度平滑，从而保证自适应校正过程的正确性。实验结果表明，我们提出的方法在各种下游任务上优于随机初始化、ImageNet 预训练和其他表示学习方法。 特别是，与直接从偏差地理监督学习表示的方法相比，证明我们的方法可以消除偏差的影响，进一步提高表示学习的效果。