Visual Question Answering On Vqa V2 Val
Métriques
Accuracy
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | Accuracy |
|---|---|
| language-models-are-general-purpose | 41.1 |
| blip-2-bootstrapping-language-image-pre | 65.2 |
| blip-2-bootstrapping-language-image-pre | 54.3 |
| multimodal-few-shot-learning-with-frozen | 29.5 |
| blip-2-bootstrapping-language-image-pre | 63.1 |
| blip-2-bootstrapping-language-image-pre | 50.1 |
| enabling-multimodal-generation-on-clip-via | 38.6 |
| blip-2-bootstrapping-language-image-pre | 62.6 |
| plug-and-play-vqa-zero-shot-vqa-by-conjoining | 63.3 |
| a-good-prompt-is-worth-millions-of-parameters | 47.7 |
| blip-2-bootstrapping-language-image-pre | 53.5 |