When SAM Meets Sonar Images
This work addresses the lack of research on SAM for sonar imaging, which is an incremental advancement for domain-specific applications in fields like underwater exploration.
The paper tackles the problem of applying the Segment Anything Model (SAM) to sonar images, where its performance declines due to domain differences, and finds that fine-tuning SAM with effective methods leads to significant improvement in automated segmentation tasks.
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.