TASAM: Terrain-and-Aware Segment Anything Model for Temporal-Scale Remote Sensing Segmentation
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Image SegmentationSimilar Papers 제목 키워드 기반
Temporally Consistent Unsupervised Segmentation for Mobile Robot Perception
Rapid progress in terrain-aware autonomous ground navigation has been driven by advances in supervised semantic segmentation. However, these methods rely on costly data collection and labor-intensive ground truth labelin…
Semantic SegmentationCaption Anything in Video: Fine-grained Object-centric Captioning via Spatiotemporal Multimodal Prompting
We present CAT-V (Caption AnyThing in Video), a training-free framework for fine-grained object-centric video captioning that enables detailed descriptions of user-selected objects through time. CAT-V integrates three ke…
Boundary DetectionObjectSemantic SegmentationVideo CaptioningVisual Representation Learning for Preference-Aware Path Planning
Autonomous mobile robots deployed in outdoor environments must reason about different types of terrain for both safety (e.g., prefer dirt over mud) and deployer preferences (e.g., prefer dirt path over flower beds). Most…
Representation LearningSemantic SegmentationMulti-stage Planning for Multi-target Surveillance using Aircrafts Equipped with Synthetic Aperture Radars Aware of Target Visibility
Generating trajectories for synthetic aperture radar (SAR)-equipped aircraft poses significant challenges due to terrain constraints, and the need for straight-flight segments to ensure high-quality imaging. Related work…
Reinforcement LearningTracking Anything with Decoupled Video Segmentation
Training data for video segmentation are expensive to annotate. This impedes extensions of end-to-end algorithms to new video segmentation tasks, especially in large-vocabulary settings. To 'track anything' without train…
Open-Vocabulary Video SegmentationOpen-World Video SegmentationPanoptic SegmentationReferring Expression Segmentation+9