MAS-SAM: Segment Any Marine Animal with Aggregated Features

arXiv:2404.15700v1 Announce Type: new
Abstract: Recently, Segment Anything Model (SAM) shows exceptional performance in generating high-quality object masks and achieving zero-shot image segmentation. However, as a versatile vision model, SAM is primarily trained with large-scale natural light images. In underwater scenes, it exhibits substantial performance degradation due to the light scattering and absorption. Meanwhile, the simplicity of the SAM's decoder might lead to the loss of fine-grained object details. To address the above issues, we propose a novel feature learning …

arxiv cs.cv cs.ro features marine sam segment type