Visual Question Answering Vqa On Coco
Métriques
ClipMatch@1
ClipMatch@5
Contains
ExactMatch
Résultats
Résultats de performance de divers modèles sur ce benchmark
Nom du modèle | ClipMatch@1 | ClipMatch@5 | Contains | ExactMatch | Paper Title | Repository |
|---|---|---|---|---|---|---|
| InstructBLIP Vicuna | 59.58 | 73.32 | 27.52 | 26.50 | Open-ended VQA benchmarking of Vision-Language models by exploiting Classification datasets and their semantic hierarchy |
0 of 1 row(s) selected.