Customizing Segmentation Foundation Model via Prompt Learning for Instance Segmentation

arXiv:2403.09199v1 Announce Type: new
Abstract: Recently, foundation models trained on massive datasets to adapt to a wide range of domains have attracted considerable attention and are actively being explored within the computer vision community. Among these, the Segment Anything Model (SAM) stands out for its remarkable progress in generalizability and flexibility for image segmentation tasks, achieved through prompt-based object mask generation. However, despite its strength, SAM faces two key limitations when applied to customized instance segmentation that segments specific objects …

abstract adapt arxiv attention community computer computer vision cs.ai cs.cv datasets domains foundation foundation model instance massive progress prompt prompt learning sam segment segment anything segment anything model segmentation type via vision