List your company

Referring Expression Comprehension on RefCOCOg 48 (test-u)

89.15AccuracySimVG-DB
75.234878.847482.4686.0726Sep 26, 2024

Evaluation results

MethodLinks
SimVG-DBVisual Encoder=ViT-L/32, Pre-train images=28K2024.0989.15
SimVG-TBVisual Encoder=ViT-L/32, Pre-train images=28K2024.0988.96
SimVG-DBVisual Encoder=ViT-B/32, Pre-train images=174K2024.0987.26
OFA-LVisual Encoder=RN1522024.0986.55
mPLUG-2Visual Encoder=ViT-L/142024.0986.42
SimVG-TBVisual Encoder=ViT-B/32, Pre-train images=174K2024.0986.28
SimVG-DBVisual Encoder=ViT-B/32, Pre-train images=28K2024.0986.23
PolyFormerVisual Encoder=Swin-L2024.0985.91
PolyFormerVisual Encoder=Swin-B2024.0984.96
GroundingDINOVisual Encoder=Swin-T2024.0984.94
UniTABVisual Encoder=RN1012024.0984.7
DQ-DETRVisual Encoder=RN1012024.0983.44
SeqTRVisual Encoder=DN532024.0983.37
MDETRVisual Encoder=RN1012024.0980.89
RefTRVisual Encoder=RN1012024.0980.01
VILLA_LVisual Encoder=RN1012024.0976.71
UNITER_LVisual Encoder=RN1012024.0975.77