Visual Entailment On Snli Ve Val
Métriques
Accuracy
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | Accuracy |
|---|---|
| how-much-can-clip-benefit-vision-and-language | 80.20 |
| visual-entailment-a-novel-task-for-fine | 70.81 |
| unifying-architectures-tasks-and-modalities | 91.0 |
| simvlm-simple-visual-language-model | 86.21 |
| uniter-learning-universal-image-text-1 | 78.98 |
| prompt-tuning-for-generative-multimodal | 90.04 |
| large-scale-adversarial-training-for-vision | 80.18 |
| coca-contrastive-captioners-are-image-text | 87.0 |
| seeing-out-of-the-box-end-to-end-pre-training | 85.00 |