AI RESEARCH
Vision Harnessing Agent for Open Ad-hoc Segmentation
arXiv CS.CV
•
ArXi:2605.19410v1 Announce Type: new Segmentation has become easy when the concept is known, requiring retrieval of a learned visual grounding from text. It remains hard for open ad-hoc concepts, where the grounding may not exist as one learned mask and must often be constructed from image evidence through parts, relations, exclusions, and collections. We propose a Vision-guided Ad-hoc Segmentation Agent (VASA), the first vision harnessing agent for open ad-hoc segmentation. VASA is