Visual Question Answering Vqa On Imagenet
Metrics
ClipMatch@1
ClipMatch@5
Contains
ExactMatch
Follow-up ClipMatch@1
Follow-up ClipMatch@5
Follow-up Contains
Follow-up ExactMatch
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | ClipMatch@1 | ClipMatch@5 | Contains | ExactMatch | Follow-up ClipMatch@1 | Follow-up ClipMatch@5 | Follow-up Contains | Follow-up ExactMatch |
|---|---|---|---|---|---|---|---|---|
| open-ended-vqa-benchmarking-of-vision | 57.10 | 77.24 | 35.49 | 0.87 | 67.22 | 83.54 | 40.31 | 2.54 |