让SAM学会看地形和时间变化，提升遥感图像分割精度
TASAM: Terrain-and-Aware Segment Anything Model for Temporal-Scale Remote Sensing Segmentation
- 引入地形先验、时序提示和多尺度融合模块，增强模型对遥感数据的理解
- 在LoveDA、iSAID、WHU-CD三个数据集上超越零样本SAM和专用模型
- 无需重训练主干网络，计算开销小，适合实际地理空间应用
Segment Anything Model (SAM) 在自然图像领域展现了出色的零样本分割能力，但在遥感数据中因复杂地形、多尺度目标和时序动态等挑战而表现不佳。本文提出TASAM，一种专为高分辨率遥感图像分割设计的地形与时序感知扩展模型。TASAM集成三个轻量级有效模块：地形感知适配器注入高程先验，时序提示生成器捕捉地表覆盖变化，多尺度融合策略提升细粒度目标分割。无需重训练SAM主干，该方法在LoveDA、iSAID、WHU-CD三个遥感基准上显著优于零样本SAM及任务特定模型，且计算开销极低。结果表明，针对领域特性的增强对基础模型至关重要，为构建更鲁棒的地理空间分割系统提供了可扩展路径。
原文摘要 · Abstract (English)
Segment Anything Model (SAM) has demonstrated impressive zero-shot segmentation capabilities across natural image domains, but it struggles to generalize to the unique challenges of remote sensing data, such as complex terrain, multi-scale objects, and temporal dynamics. In this paper, we introduce TASAM, a terrain and temporally-aware extension of SAM designed specifically for high-resolution remote sensing image segmentation. TASAM integrates three lightweight yet effective modules: a terrain-aware adapter that injects elevation priors, a temporal prompt generator that captures land-cover changes over time, and a multi-scale fusion strategy that enhances fine-grained object delineation. Without retraining the SAM backbone, our approach achieves substantial performance gains across three remote sensing benchmarks-LoveDA, iSAID, and WHU-CD-outperforming both zero-shot SAM and task-specific models with minimal computational overhead. Our results highlight the value of domain-adaptive augmentation for foundation models and offer a scalable path toward more robust geospatial segmentation.
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。