Visual Question Answering On Vcr Qa R Test
Metriken
Accuracy
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Vergleichstabelle
| Modellname | Accuracy |
|---|---|
| vl-bert-pre-training-of-generic-visual | 78.4 |
| unifying-vision-and-language-tasks-via-text | 77.8 |
| uniter-learning-universal-image-text-1 | 83.4 |
| gpt4roi-instruction-tuning-large-language | 91.0 |
| uniter-learning-universal-image-text-1 | 80.8 |
| ernie-vil-knowledge-enhanced-vision-language | 86.1 |
| kvl-bert-knowledge-enhanced-visual-and | 78.6 |
| visualbert-a-simple-and-performant-baseline | 73.2 |