List your company

Referring Expression Comprehension on RefCOCOg 48 (val-u)

87.99AccuracySimVG-DB
74.334877.879981.42584.9701Sep 26, 2024

Evaluation results

MethodLinks
SimVG-DBVisual Encoder=ViT-L/32, Pre-train images=28K2024.0987.99
SimVG-TBVisual Encoder=ViT-L/32, Pre-train images=28K2024.0987.95
SimVG-DBVisual Encoder=ViT-B/32, Pre-train images=174K2024.0986.3
SimVG-DBVisual Encoder=ViT-B/32, Pre-train images=28K2024.0985.9
OFA-LVisual Encoder=RN1522024.0985.89
mPLUG-2Visual Encoder=ViT-L/142024.0985.88
PolyFormerVisual Encoder=Swin-L2024.0985.83
SimVG-TBVisual Encoder=ViT-B/32, Pre-train images=174K2024.0985.38
UniTABVisual Encoder=RN1012024.0984.58
PolyFormerVisual Encoder=Swin-B2024.0984.46
GroundingDINOVisual Encoder=Swin-T2024.0984.15
DQ-DETRVisual Encoder=RN1012024.0982.76
SeqTRVisual Encoder=DN532024.0982.69
MDETRVisual Encoder=RN1012024.0981.64
RefTRVisual Encoder=RN1012024.0979.25
VILLA_LVisual Encoder=RN1012024.0976.18
UNITER_LVisual Encoder=RN1012024.0974.86