SAM is a segmentation model recently released by Meta AI Research and has been gaining attention quickly due to its impressive performance in generic object segmentation. However, its ability to generalize to specific scenes such as camouflaged scenes is still unknown. Camouflaged object detection (COD) involves identifying objects that are seamlessly integrated into their surroundings and has numerous practical applications in fields such as medicine, art, and agriculture. In this study, we try to ask if SAM can address the COD task and evaluate the performance of SAM on the COD benchmark by employing maximum segmentation evaluation and camouflage location evaluation. We also compare SAM's performance with 22 state-of-the-art COD methods. Our results indicate that while SAM shows promise in generic object segmentation, its performance on the COD task is limited. This presents an opportunity for further research to explore how to build a stronger SAM that may address the COD task. The results of this paper are provided in \url{https://github.com/luckybird1994/SAMCOD}.
翻译:摘要:SAM 是由 Meta AI 研究团队最近发布的分割模型,由于其在通用物体分割中的出色表现,它迅速引起了人们的关注。然而,它在特定场景下的泛化能力,例如伪装场景,仍然未知。伪装物体检测(COD)涉及识别与周围环境无缝集成的物体,在医学、艺术和农业等领域有许多实际应用。在这项研究中,我们尝试探究 SAM 是否能够解决 COD 任务,并通过采用最大分割评估和伪装位置评估来评估 SAM 在 COD 基准测试上的性能。我们还将 SAM 的性能与其他 22 种最先进的 COD 方法进行了比较。结果表明,尽管 SAM 在通用物体分割方面表现出色,但它在 COD 任务方面的表现有限。这为进一步研究提供了机会,探索如何构建更强大的 SAM,从而可以解决 COD 任务。本文的结果提供在 \url{https://github.com/luckybird1994/SAMCOD}。