AI RESEARCH
Tarot-SAM3: Training-free SAM3 for Any Referring Expression Segmentation
arXiv CS.CV
•
ArXi:2604.07916v1 Announce Type: new Referring Expression Segmentation (RES) aims to segment image regions described by natural-language expressions, serving as a bridge between vision and language understanding. Existing RES methods, however, rely heavily on large annotated datasets and are limited to either explicit or implicit expressions, hindering their ability to generalize to any referring expression. Recently, the Segment Anything Model 3 (SAM3) has shown impressive robustness in Promptable Concept Segmentation.