Referring Expression Comprehension on RefCOCOg 48 (val-u)
87.99AccuracySimVG-DB
Evaluation Results
| Method | Links | |
|---|---|---|
| SimVG-DBVisual Encoder=ViT-L/32, Pre-train images=28K2024.09 | 87.99 | |
| SimVG-TBVisual Encoder=ViT-L/32, Pre-train images=28K2024.09 | 87.95 | |
| SimVG-DBVisual Encoder=ViT-B/32, Pre-train images=174K2024.09 | 86.3 | |
| SimVG-DBVisual Encoder=ViT-B/32, Pre-train images=28K2024.09 | 85.9 | |
| OFA-LVisual Encoder=RN1522024.09 | 85.89 | |
| mPLUG-2Visual Encoder=ViT-L/142024.09 | 85.88 | |
| PolyFormerVisual Encoder=Swin-L2024.09 | 85.83 | |
| SimVG-TBVisual Encoder=ViT-B/32, Pre-train images=174K2024.09 | 85.38 | |
| UniTABVisual Encoder=RN1012024.09 | 84.58 | |
| PolyFormerVisual Encoder=Swin-B2024.09 | 84.46 | |
| GroundingDINOVisual Encoder=Swin-T2024.09 | 84.15 | |
| DQ-DETRVisual Encoder=RN1012024.09 | 82.76 | |
| SeqTRVisual Encoder=DN532024.09 | 82.69 | |
| MDETRVisual Encoder=RN1012024.09 | 81.64 | |
| RefTRVisual Encoder=RN1012024.09 | 79.25 | |
| VILLA_LVisual Encoder=RN1012024.09 | 76.18 | |
| UNITER_LVisual Encoder=RN1012024.09 | 74.86 |