Visual Grounding on RefCOCOg (test-u)
89.27AccuracyONE-PEACE
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| ONE-PEACE2023.05 | 89.27 | — | |
| OFA2023.05 | 88.78 | — | |
| FIBER2023.05 | 87.32 | — | |
| Grounding-DINO2023.05 | 87.02 | — | |
| UNICORN2023.05 | 83.93 | — | |
| SeqTRVisual Encoder=DN53, Params (M)=7.90, Pre-train images=174K2022.03 | 83.37 | — | |
| MDETRVisual Encoder=RN101, Params (M)=17.36, Pre-train images=200K2022.03 | 80.89 | — | |
| MDETR2023.05 | 80.89 | — | |
| RefTRVisual Encoder=RN101, Params (M)=17.86, Pre-train images=100K2022.03 | 80.01 | — | |
| VILLA_LVisual Encoder=RN101, Params (M)=4.6, Pre-train images=4.0M2022.03 | 76.71 | — | |
| VILLA2023.05 | 76.71 | — | |
| UNITER_LVisual Encoder=RN101, Params (M)=4.6, Pre-train images=4.0M2022.03 | 75.77 | — | |
| UNITER2023.05 | 75.77 | — | |
| VL-T52023.05 | 71.3 | — | |
| MDETR2023.02 | — | 80.89 | |
| mPLUG-22023.02 | — | 85.14 | |
| OFA Large2023.02 | — | 85.2 | |
| UNICORN2023.02 | — | 83.93 | |
| UNITER2023.02 | — | 75.77 | |
| VILLA2023.02 | — | 76.71 |