Referring Expression Comprehension on RefCOCO+ 80 (val)
87.43AccuracySimVG-TB
Evaluation Results
| Method | Links | |
|---|---|---|
| SimVG-TBVisual Encoder=ViT-L/32, Pre-train images=28K2024.09 | 87.43 | |
| SimVG-DBVisual Encoder=ViT-L/32, Pre-train images=28K2024.09 | 87.28 | |
| mPLUG-2Visual Encoder=ViT-L/142024.09 | 86.02 | |
| OFA-LVisual Encoder=RN1522024.09 | 85.8 | |
| PolyFormerVisual Encoder=Swin-L2024.09 | 84.98 | |
| SimVG-DBVisual Encoder=ViT-B/32, Pre-train images=174K2024.09 | 84.83 | |
| SimVG-DBVisual Encoder=ViT-B/32, Pre-train images=28K2024.09 | 84.17 | |
| PolyFormerVisual Encoder=Swin-B2024.09 | 83.73 | |
| SimVG-TBVisual Encoder=ViT-B/32, Pre-train images=174K2024.09 | 83.54 | |
| DQ-DETRVisual Encoder=RN1012024.09 | 81.66 | |
| GroundingDINOVisual Encoder=Swin-T2024.09 | 81.09 | |
| UniTABVisual Encoder=RN1012024.09 | 80.97 | |
| MDETRVisual Encoder=RN1012024.09 | 79.52 | |
| SeqTRVisual Encoder=DN532024.09 | 78.69 | |
| RefTRVisual Encoder=RN1012024.09 | 77.55 | |
| VILLA_LVisual Encoder=RN1012024.09 | 76.17 | |
| UNITER_LVisual Encoder=RN1012024.09 | 75.9 |