提出一种新采样增广法，提升遥感时序数据对比学习效果。
Resampling Augmentation for Time Series Contrastive Learning: Application to Remote Sensing
- 通过上采样和不重叠子序列提取生成正样本对。
- 在S2-Agri100上达到当前最佳性能，无需空间或时间编码。
- 方法简单高效，适合资源受限的遥感时序学习场景。
由于卫星图像时序数据（SITS）数量庞大但标注数据稀缺，对比自监督预训练成为利用海量无标签数据的自然选择。然而，为时序数据设计有效的数据增广仍具挑战。本文提出一种基于重采样的新增广策略，通过上采样时序并提取不重叠子序列，在保持时间覆盖的前提下生成正样本对。我们在多个农业分类基准上验证该方法，使用哨兵2号影像，结果表明其优于常见的抖动、缩放和掩码等增广方式。此外，在S2-Agri100数据集上，仅使用时序信息即达到当前最优性能，超越更复杂的掩码式自监督框架。本方法为遥感时序数据提供了一种简单而有效的对比学习增广方案。
原文摘要 · Abstract (English)
Given the abundance of unlabeled Satellite Image Time Series (SITS) and the scarcity of labeled data, contrastive self-supervised pretraining emerges as a natural tool to leverage this vast quantity of unlabeled data. However, designing effective data augmentations for contrastive learning remains challenging for time series. We introduce a novel resampling-based augmentation strategy that generates positive pairs by upsampling time series and extracting disjoint subsequences while preserving temporal coverage. We validate our approach on multiple agricultural classification benchmarks using Sentinel-2 imagery, showing that it outperforms common alternatives such as jittering, resizing, and masking. Further, we achieve state-of-the-art performance on the S2-Agri100 dataset without employing spatial information or temporal encodings, surpassing more complex masked-based SSL frameworks. Our method offers a simple, yet effective, contrastive learning augmentation for remote sensing time series.
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。