Referring Expression Comprehension on RefCOCOg 48 (test-u)
89.15AccuracySimVG-DB
Evaluation Results
| Method | Links | |
|---|---|---|
| SimVG-DBVisual Encoder=ViT-L/32, Pre-train images=28K2024.09 | 89.15 | |
| SimVG-TBVisual Encoder=ViT-L/32, Pre-train images=28K2024.09 | 88.96 | |
| SimVG-DBVisual Encoder=ViT-B/32, Pre-train images=174K2024.09 | 87.26 | |
| OFA-LVisual Encoder=RN1522024.09 | 86.55 | |
| mPLUG-2Visual Encoder=ViT-L/142024.09 | 86.42 | |
| SimVG-TBVisual Encoder=ViT-B/32, Pre-train images=174K2024.09 | 86.28 | |
| SimVG-DBVisual Encoder=ViT-B/32, Pre-train images=28K2024.09 | 86.23 | |
| PolyFormerVisual Encoder=Swin-L2024.09 | 85.91 | |
| PolyFormerVisual Encoder=Swin-B2024.09 | 84.96 | |
| GroundingDINOVisual Encoder=Swin-T2024.09 | 84.94 | |
| UniTABVisual Encoder=RN1012024.09 | 84.7 | |
| DQ-DETRVisual Encoder=RN1012024.09 | 83.44 | |
| SeqTRVisual Encoder=DN532024.09 | 83.37 | |
| MDETRVisual Encoder=RN1012024.09 | 80.89 | |
| RefTRVisual Encoder=RN1012024.09 | 80.01 | |
| VILLA_LVisual Encoder=RN1012024.09 | 76.71 | |
| UNITER_LVisual Encoder=RN1012024.09 | 75.77 |