Referring Expression Comprehension on RefCOCO 80 (testA)
94.86AccuracySimVG-TB
Evaluation Results
| Method | Links | |
|---|---|---|
| SimVG-TBVisual Encoder=ViT-L/32, Pre-train images=28K2024.09 | 94.86 | |
| SimVG-DBVisual Encoder=ViT-L/32, Pre-train images=28K2024.09 | 94.7 | |
| mPLUG-2Visual Encoder=ViT-L/142024.09 | 94.51 | |
| SimVG-DBVisual Encoder=ViT-B/32, Pre-train images=174K2024.09 | 93.65 | |
| OFA-LVisual Encoder=RN1522024.09 | 92.93 | |
| PolyFormerVisual Encoder=Swin-L2024.09 | 92.89 | |
| SimVG-TBVisual Encoder=ViT-B/32, Pre-train images=174K2024.09 | 92.8 | |
| SimVG-DBVisual Encoder=ViT-B/32, Pre-train images=28K2024.09 | 92.68 | |
| GroundingDINOVisual Encoder=Swin-T2024.09 | 91.86 | |
| PolyFormerVisual Encoder=Swin-B2024.09 | 91.73 | |
| UniTABVisual Encoder=RN1012024.09 | 91.06 | |
| DQ-DETRVisual Encoder=RN1012024.09 | 91.04 | |
| SeqTRVisual Encoder=DN532024.09 | 90.15 | |
| MDETRVisual Encoder=RN1012024.09 | 89.58 | |
| RefTRVisual Encoder=RN1012024.09 | 88.73 | |
| VILLA_LVisual Encoder=RN1012024.09 | 87.48 | |
| UNITER_LVisual Encoder=RN1012024.09 | 87.04 |