Fantastic Animals and Where to Find Them: Segment Any Marine Animal with Dual SAM

arXiv:2404.04996v1 Announce Type: new
Abstract: As an important pillar of underwater intelligence, Marine Animal Segmentation (MAS) involves segmenting animals within marine environments. Previous methods don't excel in extracting long-range contextual features and overlook the connectivity between discrete pixels. Recently, Segment Anything Model (SAM) offers a universal framework for general segmentation tasks. Unfortunately, trained with natural images, SAM does not obtain the prior knowledge from marine images. In addition, the single-position prompt of SAM is very insufficient for prior guidance. To …

animals arxiv cs.cv cs.mm marine sam segment them type