List your company

Referring Expression Comprehension on RefCOCO+ 80 (val)

87.43AccuracySimVG-TB
75.438878.551981.66584.7781Sep 26, 2024

Evaluation results

MethodLinks
SimVG-TBVisual Encoder=ViT-L/32, Pre-train images=28K2024.0987.43
SimVG-DBVisual Encoder=ViT-L/32, Pre-train images=28K2024.0987.28
mPLUG-2Visual Encoder=ViT-L/142024.0986.02
OFA-LVisual Encoder=RN1522024.0985.8
PolyFormerVisual Encoder=Swin-L2024.0984.98
SimVG-DBVisual Encoder=ViT-B/32, Pre-train images=174K2024.0984.83
SimVG-DBVisual Encoder=ViT-B/32, Pre-train images=28K2024.0984.17
PolyFormerVisual Encoder=Swin-B2024.0983.73
SimVG-TBVisual Encoder=ViT-B/32, Pre-train images=174K2024.0983.54
DQ-DETRVisual Encoder=RN1012024.0981.66
GroundingDINOVisual Encoder=Swin-T2024.0981.09
UniTABVisual Encoder=RN1012024.0980.97
MDETRVisual Encoder=RN1012024.0979.52
SeqTRVisual Encoder=DN532024.0978.69
RefTRVisual Encoder=RN1012024.0977.55
VILLA_LVisual Encoder=RN1012024.0976.17
UNITER_LVisual Encoder=RN1012024.0975.9