Florence-2-large-ft

Reported on 3 benchmarks across 1 task · 1 paper · 3 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision3 results

Visual GroundingonRefCOCO+ test B
Accuracy (%)· uses extra data· 2023-11-10
92
SOTA
Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks arXiv:2311.06242
Visual GroundingonRefCOCO+ val
Accuracy (%)· uses extra data· 2023-11-10
93.4
SOTA
Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks arXiv:2311.06242
Visual GroundingonRefCOCO+ testA
Accuracy (%)· uses extra data· 2023-11-10
95.3
SOTA
Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks arXiv:2311.06242