What type of study is this?

This is a Quantitative Study study.

October 2, 2025Open Access

TASAM: Terrain-and-Aware Segment Anything Model for Temporal-Scale Remote Sensing Segmentation

Key Points

TASAM achieved significant performance gains in remote sensing segmentation without retraining the SAM backbone, enhancing flexibility.
On benchmarks like LoveDA and WHU-CD, TASAM outperformed both the original SAM and specialized models under various conditions.
The approach involves novel modules for injecting terrain data, generating temporal prompts, and fusing multi-scale information effectively.
Our findings suggest that domain-adaptive strategies can lead to substantial improvements in segmentation tasks in complex environments.

Abstract

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.

TASAM: Terrain-and-Aware Segment Anything Model for Temporal-Scale Remote Sensing Segmentation

Key Points

Abstract

Cite This Study

Also Consider

Also Consider