With breakthroughs in large-scale modeling, the Segment Anything Model (SAM) and its extensions have been attempted for applications in various underwater visualization tasks in marine sciences, and have had a significant impact on the academic community. Recently, Meta has further developed the Segment Anything Model 2 (SAM2), which significantly improves running speed and segmentation accuracy compared to its predecessor. This report aims to explore the potential of SAM2 in marine science by evaluating it on the underwater instance segmentation benchmark datasets UIIS and USIS10K. The experiments show that the performance of SAM2 is extremely dependent on the type of user-provided prompts. When using the ground truth bounding box as prompt, SAM2 performed excellently in the underwater instance segmentation domain. However, when running in automatic mode, SAM2's ability with point prompts to sense and segment underwater instances is significantly degraded. It is hoped that this paper will inspire researchers to further explore the SAM model family in the underwater domain. The results and evaluation codes in this paper are available at https://github.com/LiamLian0727/UnderwaterSAM2Eval.

翻译：随着大规模建模技术的突破，Segment Anything Model（SAM）及其扩展模型已在海洋科学中的各类水下可视化任务中得到尝试应用，并对学术界产生了重要影响。近期，Meta 公司进一步开发了 Segment Anything Model 2（SAM2），其运行速度和分割精度相较于前代模型均有显著提升。本报告旨在通过在水下实例分割基准数据集 UIIS 和 USIS10K 上对 SAM2 进行评估，以探索其在海洋科学中的潜力。实验表明，SAM2 的性能极大程度依赖于用户提供的提示类型。当使用真实标注边界框作为提示时，SAM2 在水下实例分割领域表现优异。然而，在自动模式下运行时，SAM2 利用点提示感知和分割水下实例的能力显著下降。希望本文能启发研究者们在水下领域进一步探索 SAM 模型家族。本文的结果与评估代码公开于 https://github.com/LiamLian0727/UnderwaterSAM2Eval。