Referring Expression Comprehension on RefCOCOg (val-g)
80.42AccuracySimVG-DB
Evaluation Results
| Method | Links | |
|---|---|---|
| SimVG-DBVisual Encoder=ViT-L/32, Time (ms)=1162024.09 | 80.42 | |
| SimVG-TBVisual Encoder=ViT-L/32, Time (ms)=1012024.09 | 79.34 | |
| SimVG-DBVisual Encoder=ViT-B/32, Time (ms)=522024.09 | 78.81 | |
| SimVG-TBVisual Encoder=ViT-B/32, Time (ms)=442024.09 | 77.66 | |
| TransCPVisual Encoder=RN50, Time (ms)=74*2024.09 | 72.6 | |
| VLTVGVisual Encoder=RN50, Time (ms)=79*2024.09 | 72.53 | |
| Dyn.MDETRVisual Encoder=ViT-B/162024.09 | 72.21 | |
| SeqTRVisual Encoder=DN53, Time (ms)=502024.09 | 71.5 | |
| DGAVisual Encoder=VGG16, Time (ms)=3412024.09 | 69.07 | |
| TransVGVisual Encoder=RN101, Time (ms)=622024.09 | 67.02 | |
| ReSCLVisual Encoder=DN53, Time (ms)=362024.09 | 63.12 | |
| LBYLVisual Encoder=DN53, Time (ms)=302024.09 | 62.7 | |
| VGTRVisual Encoder=RN502024.09 | 61.64 | |
| NMTreeVisual Encoder=RN1012024.09 | 57.52 |