[论文解读] Wetland mapping from sparse annotations with satellite image time series and temporal-aware segment anything model

Shuai Yuan, Tianwu Lin+9 more|arXiv (Cornell University)|Jan 16, 2026

Remote Sensing in Agriculture被引用 0

一句话总结

WetSAM 将稀疏点监督与卫星时序相结合，以自适应 SAM 进行动态湿地分割，在不同区域实现高准确性。

ABSTRACT

Accurate wetland mapping is essential for ecosystem monitoring, yet dense pixel-level annotation is prohibitively expensive and practical applications usually rely on sparse point labels, under which existing deep learning models perform poorly, while strong seasonal and inter-annual wetland dynamics further render single-date imagery inadequate and lead to significant mapping errors; although foundation models such as SAM show promising generalization from point prompts, they are inherently designed for static images and fail to model temporal information, resulting in fragmented masks in heterogeneous wetlands. To overcome these limitations, we propose WetSAM, a SAM-based framework that integrates satellite image time series for wetland mapping from sparse point supervision through a dual-branch design, where a temporally prompted branch extends SAM with hierarchical adapters and dynamic temporal aggregation to disentangle wetland characteristics from phenological variability, and a spatial branch employs a temporally constrained region-growing strategy to generate reliable dense pseudo-labels, while a bidirectional consistency regularization jointly optimizes both branches. Extensive experiments across eight global regions of approximately 5,000 km2 each demonstrate that WetSAM substantially outperforms state-of-the-art methods, achieving an average F1-score of 85.58%, and delivering accurate and structurally consistent wetland segmentation with minimal labeling effort, highlighting its strong generalization capability and potential for scalable, low-cost, high-resolution wetland mapping.

研究动机与目标

• 在强时序动态下解决用稀疏点标签映射湿地的挑战。
• 将 Segment Anything Model (SAM) 适配于卫星时序数据以实现湿地界定。
• 通过时空区域增长方法，从稀疏点生成空间一致的密集监督。
• 在时间和空间分支之间强制一致性，以提升分割质量。
• 在多样化的全球湿地上验证 WetSAM，以展示可扩展性与泛化能力。

提出的方法

• 提出一个双分支的 WetSAM 框架，包含时间适配分支和空间区域增长分支。
• 在时间分支中，实现分层多尺度适配器和动态时间聚合模块，将时序分解为趋势和高频事件。
• 用正弦嵌入对时间位置进行编码，并与可学习的趋势—剩余分解通过 GRU 和多头注意力融合。
• 复用 SAM 解码器，将融合后的时间感知特征作为查询，点基语义上下文令牌作为键/值。
• 在空间分支中，从稀疏种子进行带时间约束的区域增长，生成用于训练专用头的密集伪标签。
• 在空间预测上使用 Lovász-Softmax 损失，在时间预测上使用逐点交叉熵损失，并引入预测对齐损失以耦合两头。
• 使用稀疏点进行训练，进行迭代伪标签细化，并采用非可微区域增长伪标签生成器以强化空间一致性。

Figure 1: Overview. We propose an end-to-end, single- stage model for wetland mapping from satellite image time series under sparse point supervision. Note the difficulty of semantic segmentation of wetlands from a single image, highlighting the need for modeling temporal dynamics and spatial contex

实验结果

研究问题

• RQ1 是否可以利用时序影像的稀疏点监督来生成准确的湿地地图？
• RQ2 如何将 SAM 扩展到遥感时序数据以捕捉湿地物候和水文？
• RQ3 区域增长策略是否能够从稀疏标注中产生可靠的密集监督用于湿地？
• RQ4 强制时间预测与空间预测之间的一致性是否能提升分割质量？

主要发现

• WetSAM 在八个全球湿地上的平均 F1-score 为 85.58%。
• 在最小标注努力下，WetSAM 的表现优于现有方法基线。
• 将时间分解为趋势和高频事件有助于将湿地与物候变异区分开来。
• 基于时间引导的区域增长提供密集、结构上连贯的伪标签，从而改善边界界定。
• 双向一致性正则化使时间与空间预测对齐以实现鲁棒分割。
• 展示了高分辨率湿地映射的强泛化与可扩展性。

Figure 2: The WetSAM framework. (a) is the overview of the framework. (b) is the detailed architecture of the Encoder.