List your company

Referring Expression Comprehension on RefCOCO 80 (testA)

94.86AccuracySimVG-TB
86.727288.838690.9593.0614Sep 26, 2024

Evaluation results

MethodLinks
SimVG-TBVisual Encoder=ViT-L/32, Pre-train images=28K2024.0994.86
SimVG-DBVisual Encoder=ViT-L/32, Pre-train images=28K2024.0994.7
mPLUG-2Visual Encoder=ViT-L/142024.0994.51
SimVG-DBVisual Encoder=ViT-B/32, Pre-train images=174K2024.0993.65
OFA-LVisual Encoder=RN1522024.0992.93
PolyFormerVisual Encoder=Swin-L2024.0992.89
SimVG-TBVisual Encoder=ViT-B/32, Pre-train images=174K2024.0992.8
SimVG-DBVisual Encoder=ViT-B/32, Pre-train images=28K2024.0992.68
GroundingDINOVisual Encoder=Swin-T2024.0991.86
PolyFormerVisual Encoder=Swin-B2024.0991.73
UniTABVisual Encoder=RN1012024.0991.06
DQ-DETRVisual Encoder=RN1012024.0991.04
SeqTRVisual Encoder=DN532024.0990.15
MDETRVisual Encoder=RN1012024.0989.58
RefTRVisual Encoder=RN1012024.0988.73
VILLA_LVisual Encoder=RN1012024.0987.48
UNITER_LVisual Encoder=RN1012024.0987.04