Multiple Choice Visual Question Answering on AOKVQA
68.9Accuracy (MC)BLIP-2 ViT-G + LSKD
Evaluation Results
| Method | Links | |
|---|---|---|
| BLIP-2 ViT-G + LSKDEvaluation Protocol=Zero-shot, Backbone=ViT-G2023.12 | 68.9 | |
| BLIP-2 ViT-GEvaluation Protocol=Zero-shot, Backbone=ViT-G2023.12 | 68 | |
| BLIP-2 ViT-LEvaluation Protocol=Zero-shot, Backbone=ViT-L2023.12 | 65 | |
| BLIP ViT-LEvaluation Protocol=Zero-shot, Backbone=ViT-L2023.12 | 61.3 | |
| CLIP ViT-L-14x336Evaluation Protocol=Zero-shot, Backbone=ViT-L-14x3362023.12 | 61 | |
| CLIP ViT-B-16*Evaluation Protocol=Zero-shot, Backbone=ViT-B-162023.12 | 58.3 |