Visual Commonsense Comparison on Sherlock
29.7Comparison ScoreBLIP-2 ViT-G + LSKD
Evaluation results
| Method | Links | |
|---|---|---|
| BLIP-2 ViT-G + LSKDEvaluation Protocol=Zero-shot, Backbone=ViT-G2023.12 | 29.7 | |
| BLIP-2 ViT-GEvaluation Protocol=Zero-shot, Backbone=ViT-G2023.12 | 19.5 | |
| BLIP-2 ViT-LEvaluation Protocol=Zero-shot, Backbone=ViT-L2023.12 | 18.7 | |
| BLIP ViT-LEvaluation Protocol=Zero-shot, Backbone=ViT-L2023.12 | 18.6 | |
| CLIP ViT-L-14x336Evaluation Protocol=Zero-shot, Backbone=ViT-L-14x3362023.12 | 10.9 | |
| CLIP ViT-B-16*Evaluation Protocol=Zero-shot, Backbone=ViT-B-162023.12 | 9.9 |