List your company
ResearchFormerly WizWand

Referring Expression Comprehension on RefCOCO 80 (val)

92.99AccuracySimVG-TB
80.946884.073487.290.3266Sep 26, 2024
Updated 8mo ago

Evaluation results

MethodLinks
SimVG-TBVisual Encoder=ViT-L/32, Params (M)=1.58, Pre-train images=28K, Time (ms)=1012024.0992.99
SimVG-DBVisual Encoder=ViT-L/32, Params (M)=6.32, Pre-train images=28K, Time (ms)=1162024.0992.93
mPLUG-2Visual Encoder=ViT-L/14, Pre-train images=14M2024.0992.4
SimVG-DBVisual Encoder=ViT-B/32, Params (M)=6.32, Pre-train images=174K, Time (ms)=522024.0991.47
SimVG-DBVisual Encoder=ViT-B/32, Params (M)=6.32, Pre-train images=28K, Time (ms)=522024.0990.98
SimVG-TBVisual Encoder=ViT-B/32, Params (M)=1.58, Pre-train images=174K, Time (ms)=442024.0990.59
PolyFormerVisual Encoder=Swin-L, Pre-train images=174K2024.0990.38
OFA-LVisual Encoder=RN152, Pre-train images=20M2024.0990.05
PolyFormerVisual Encoder=Swin-B, Pre-train images=174K2024.0989.73
GroundingDINOVisual Encoder=Swin-T, Pre-train images=200K, Time (ms)=1202024.0989.19
DQ-DETRVisual Encoder=RN101, Pre-train images=200K2024.0988.63
UniTABVisual Encoder=RN101, Pre-train images=200K2024.0988.59
SeqTRVisual Encoder=DN53, Params (M)=7.90, Pre-train images=174K, Time (ms)=502024.0987
MDETRVisual Encoder=RN101, Params (M)=17.36, Pre-train images=200K, Time (ms)=1082024.0986.75
RefTRVisual Encoder=RN101, Params (M)=17.86, Pre-train images=100K, Time (ms)=402024.0985.65
VILLA_LVisual Encoder=RN101, Pre-train images=4.6M2024.0982.39
UNITER_LVisual Encoder=RN101, Pre-train images=4.6M2024.0981.41