Localization on RefCOCO
75.9AccuracyVanilla
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| VanillaVisual Token Budget=576, FLOPs (T)=4.292026.02 | 75.9 | 100 | |
| SwiftVLMVisual Token Budget=192, FLOPs (T)=1.752026.02 | 66.6 | 87.7 | |
| SwiftVLMVisual Token Budget=128, FLOPs (T)=1.312026.02 | 55.2 | 72.7 | |
| FEATHERVisual Token Budget=192, FLOPs (T)=1.822026.02 | 52 | 68.5 | |
| FEATHERVisual Token Budget=128, FLOPs (T)=1.442026.02 | 39 | 51.4 | |
| FastVVisual Token Budget=192, FLOPs (T)=1.712026.02 | 30.6 | 40.3 | |
| PDropVisual Token Budget=192, FLOPs (T)=1.722026.02 | 22.2 | 29.2 | |
| FastVVisual Token Budget=128, FLOPs (T)=1.292026.02 | 12.8 | 16.9 | |
| SparseVLMVisual Token Budget=192, FLOPs (T)=1.722026.02 | 8.7 | 11.5 | |
| VisionZipVisual Token Budget=192, FLOPs (T)=1.712026.02 | 7 | 9.2 | |
| SparseVLMVisual Token Budget=128, FLOPs (T)=1.32026.02 | 4.8 | 6.3 | |
| VisionZipVisual Token Budget=128, FLOPs (T)=1.292026.02 | 4.6 | 6 | |
| PDropVisual Token Budget=128, FLOPs (T)=1.282026.02 | 3 | 4 |