Referring Expression Comprehension on RefCOCO 80 (testB)
90.28AccuracySimVG-DB
Evaluation Results
| Method | Links | |
|---|---|---|
| SimVG-DBVisual Encoder=ViT-L/32, Pre-train images=28K2024.09 | 90.28 | |
| SimVG-TBVisual Encoder=ViT-L/32, Pre-train images=28K2024.09 | 90.12 | |
| mPLUG-2Visual Encoder=ViT-L/142024.09 | 88.42 | |
| SimVG-DBVisual Encoder=ViT-B/32, Pre-train images=28K2024.09 | 87.94 | |
| SimVG-DBVisual Encoder=ViT-B/32, Pre-train images=174K2024.09 | 87.94 | |
| PolyFormerVisual Encoder=Swin-L2024.09 | 87.16 | |
| SimVG-TBVisual Encoder=ViT-B/32, Pre-train images=174K2024.09 | 87.04 | |
| PolyFormerVisual Encoder=Swin-B2024.09 | 86.03 | |
| GroundingDINOVisual Encoder=Swin-T2024.09 | 85.99 | |
| OFA-LVisual Encoder=RN1522024.09 | 85.26 | |
| UniTABVisual Encoder=RN1012024.09 | 83.75 | |
| SeqTRVisual Encoder=DN532024.09 | 83.59 | |
| DQ-DETRVisual Encoder=RN1012024.09 | 83.51 | |
| MDETRVisual Encoder=RN1012024.09 | 81.41 | |
| RefTRVisual Encoder=RN1012024.09 | 81.16 | |
| VILLA_LVisual Encoder=RN1012024.09 | 74.84 | |
| UNITER_LVisual Encoder=RN1012024.09 | 74.17 |