Visual Entailment On Snli Ve Test
Métriques
Accuracy
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | Accuracy |
|---|---|
| uniter-learning-universal-image-text-1 | 78.98 |
| visual-entailment-a-novel-task-for-fine | 70.47 |
| multimodal-adaptive-distillation-for | 80.32 |
| simvlm-simple-visual-language-model | 86.32 |
| seeing-out-of-the-box-end-to-end-pre-training | 84.95 |
| prompt-tuning-for-generative-multimodal | 90.12 |
| coca-contrastive-captioners-are-image-text | 87.1 |
| unifying-architectures-tasks-and-modalities | 91.2 |