English

When SAM Meets Sonar Images

Computer Vision and Pattern Recognition 2023-06-27 v1

Abstract

Segment Anything Model (SAM) has revolutionized the way of segmentation. However, SAM's performance may decline when applied to tasks involving domains that differ from natural images. Nonetheless, by employing fine-tuning techniques, SAM exhibits promising capabilities in specific domains, such as medicine and planetary science. Notably, there is a lack of research on the application of SAM to sonar imaging. In this paper, we aim to address this gap by conducting a comprehensive investigation of SAM's performance on sonar images. Specifically, we evaluate SAM using various settings on sonar images. Additionally, we fine-tune SAM using effective methods both with prompts and for semantic segmentation, thereby expanding its applicability to tasks requiring automated segmentation. Experimental results demonstrate a significant improvement in the performance of the fine-tuned SAM.

Keywords

Cite

@article{arxiv.2306.14109,
  title  = {When SAM Meets Sonar Images},
  author = {Lin Wang and Xiufen Ye and Liqiang Zhu and Weijie Wu and Jianguo Zhang and Huiming Xing and Chao Hu},
  journal= {arXiv preprint arXiv:2306.14109},
  year   = {2023}
}

Comments

12 pages, 3 figures

R2 v1 2026-06-28T11:13:39.882Z