NeighborMAE：在掩码自编码器预训练中利用相邻对地观测图像间的空间依赖
NeighborMAE: Exploiting Spatial Dependencies between Neighboring Earth Observation Images in Masked Autoencoders Pretraining
把「相邻区域图像」作为联合重建目标引入 MAE 预训练，并配合动态掩码比例与像素损失权重，可直接迁移到遥感、航拍等大幅面连续场景的预训练流程中，替代单图独立掩码的做法。
原文依据 we propose NeighborMAE, which learns spatial dependencies by joint reconstruction of neighboring Earth Observation images
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论掩码图像建模一直是从大规模无标注对地观测图像中学习表征的最受关注的自监督学习范式之一。尽管将多模态与多时相对地观测数据纳入掩码图像建模已被广泛探索，但从相邻区域拍摄的图像之间的空间依赖关系仍被大幅忽视。由于地球表面是连续的，相邻图像高度相关，可为自监督学习提供丰富的上下文信息。为填补这一空白，我们提出 NeighborMAE，通过联合重建相邻对地观测图像来学习空间依赖。为确保重建任务保持足够的难度，我们采用一种启发式策略动态调整掩码比例与像素级损失权重。在多种预训练数据集与下游任务上的实验结果表明，NeighborMAE 显著优于现有基线，凸显了相邻图像在对地观测掩码图像建模中的价值以及我们所设计方法的有效性。代码已发布于 https://github.com/LeungTsang/NeighborMAE。
英文原文摘要 1181 字符
Masked Image Modeling has been one of the most popular self-supervised learning paradigms to learn representations from large-scale, unlabeled Earth Observation images. While incorporating multi-modal and multi-temporal Earth Observation data into Masked Image Modeling has been widely explored, the spatial dependencies between images captured from neighboring areas remains largely overlooked. Since the Earth's surface is continuous, neighboring images are highly related and offer rich contextual information for self-supervised learning. To close this gap, we propose NeighborMAE, which learns spatial dependencies by joint reconstruction of neighboring Earth Observation images. To ensure that the reconstruction remains challenging, we leverage a heuristic strategy to dynamically adjust the mask ratio and the pixel-level loss weight. Experimental results across various pretraining datasets and downstream tasks show that NeighborMAE significantly outperforms existing baselines, underscoring the value of neighboring images in Masked Image Modeling for Earth Observation and the efficacy of our designs. Our code is available on https://github.com/LeungTsang/NeighborMAE.