Visual Question Answering On Vqa X
Metriken
Accuracy
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Modellname | Accuracy | Paper Title | Repository |
|---|---|---|---|
| OFA-X | 91.2 | Harnessing the Power of Multi-Task Pretraining for Ground-Truth Level Natural Language Explanations | |
| OFA-X-MT | 92.6 | Harnessing the Power of Multi-Task Pretraining for Ground-Truth Level Natural Language Explanations |
0 of 2 row(s) selected.