Visual Question Answering On Vqa V2 Val 1
Metrics
Accuracy
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | Accuracy |
|---|---|
| blip-2-bootstrapping-language-image-pre | 81.55 |
| blip-2-bootstrapping-language-image-pre | 82.19 |
| learning-to-localize-objects-improves-spatial | 55.9 |
| blip-2-bootstrapping-language-image-pre | 81.59 |