Visual Question Answering On Vizwiz 2020
Metrics
average_precision
f1_score
Results
Performance results of various models on this benchmark
| Paper Title | |||
|---|---|---|---|
| CLIP-Ensemble | 84.13 | - | Less Is More: Linear Layers on CLIP Features as Powerful VizWiz Model |
| CLIP-Single | 82.86 | - | Less Is More: Linear Layers on CLIP Features as Powerful VizWiz Model |
| VT-Transformer (MUL) | 76.96 | 67.26 | - |
| VT-Transformer (CAT) | 74.91 | 66.7 | - |
| BERT-RG-Regression | 52.22 | 41.85 | - |
| VWTest1 | 26.84 | 42.32 | - |
0 of 6 row(s) selected.