A modular ground-then-segment pipeline using Florence-2-base and MobileSAM reaches 73.64 mIoU on a repository-specific RefCOCO validation subset at 22.8 cached-image queries per second.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
VespaSeg: A Resource-Aware Ground-then-Segment Pipeline for Referring Expression Segmentation
A modular ground-then-segment pipeline using Florence-2-base and MobileSAM reaches 73.64 mIoU on a repository-specific RefCOCO validation subset at 22.8 cached-image queries per second.