Segment Any Object Model (SAOM): Real-to-Simulation Fine-Tuning Strategy for Multi-Class Multi-Instance Segmentation

arXiv:2403.10780v1 Announce Type: new
Abstract: Multi-class multi-instance segmentation is the task of identifying masks for multiple object classes and multiple instances of the same class within an image. The foundational Segment Anything Model (SAM) is designed for promptable multi-class multi-instance segmentation but tends to output part or sub-part masks in the "everything" mode for various real-world applications. Whole object segmentation masks play a crucial role for indoor scene understanding, especially in robotics applications. We propose a new domain invariant Real-to-Simulation …

abstract arxiv class cs.ai cs.cv fine-tuning image instance instances masks multiple object part sam segment segment anything segment anything model segmentation simulation strategy type