EUVIMEDEUVIMED entdecken
Crossref

Prompt-Free Efficient Adaptation of Segment Anything Model for Remote Sensing Landslide Detection

Zuolei Li, Xingyu Gao, Zhenyu Chen, Yawen Duan, Fei Yang

IEEE Transactions on Circuits and Systems for Video Technology · 2026-07 · 36 (7) · 10564-10576

DOI: 10.1109/tcsvt.2026.3686175 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2026-07. Verfasst von Zuolei Li und 4 weiteren Autor:innen. Die Arbeit nennt 59 Literaturangaben. Gefördert von: Brain Science and Brain-like Intelligence Technology—National Science and Technology Major Project, National Natural Science Foundation of China, National Key Research and Development Program of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Landslides pose serious risks to human safety and infrastructure, making accurate and timely detection essential for disaster assessment. Although deep learning has advanced landslide recognition from remote sensing imagery, existing methods typically rely on task-specific designs, which limit their generalization ability across diverse geographic environments. The Segment Anything Model (SAM) offers strong generalization and zero-shot segmentation ability, yet its dependence on manually provided prompts and limited suitability for remote sensing imagery constrain its effectiveness in landslide detection. To address these limitations, we propose PF-SAM, a prompt-free and parameter-efficient adaptation framework tailored for landslide segmentation. PF-SAM eliminates manual prompts by automatically generating the prompt embeddings that drive SAM’s segmentation process and adapting SAM to landslide remote sensing data. Specifically, we first propose the CNN-Token Adapter, which extracts multi-scale CNN features and transforms them into prompt tokens, providing SAM with localized geometric and textural cues essential for detecting landslides of diverse shapes and sizes. Then, we propose the Global Prompt Generation Mechanism (GPGM) that further enhances segmentation: the Dense Prompt Generation Module (DPGM) generates the coarse mask as the dense prompt to guide SAM toward the correct landslide regions, while the Sparse Prompt Generation Module (SPGM) selects high-confidence embeddings to generate sparse prompts that enhance the precise localization of landslide regions. Extensive experiments on multiple landslide datasets show that PF-SAM achieves state-of-the-art performance, substantially surpassing existing methods in detection accuracy and robustness.

Förderung

  • Brain Science and Brain-like Intelligence Technology—National Science and Technology Major Project
  • National Natural Science Foundation of China
  • National Key Research and Development Program of China
  • Geological Survey Program of China
  • numerical calculations in this study were carried out on the ORISE Supercomputer

Zitieren

APA

Li, Z., Gao, X., Chen, Z., Duan, Y., & Yang, F. (2026). Prompt-Free Efficient Adaptation of Segment Anything Model for Remote Sensing Landslide Detection. IEEE Transactions on Circuits and Systems for Video Technology, 36(7), 10564-10576. https://doi.org/10.1109/tcsvt.2026.3686175

Vancouver

Li Z, Gao X, Chen Z, Duan Y, Yang F. Prompt-Free Efficient Adaptation of Segment Anything Model for Remote Sensing Landslide Detection. IEEE Transactions on Circuits and Systems for Video Technology. 2026;36(7):10564-10576. doi:10.1109/tcsvt.2026.3686175

BibTeX
@article{Li2026,
  author = {Li, Zuolei and Gao, Xingyu and Chen, Zhenyu and Duan, Yawen and Yang, Fei},
  title = {Prompt-Free Efficient Adaptation of Segment Anything Model for Remote Sensing Landslide Detection},
  journal = {IEEE Transactions on Circuits and Systems for Video Technology},
  year = {2026},
  volume = {36},
  number = {7},
  pages = {10564--10576},
  doi = {10.1109/tcsvt.2026.3686175}
}
Kostenlos starten →