Visual Question Answering Vqa On Whoops
Metrics
BEM
Exact Match
Results
Performance results of various models on this benchmark
| Paper Title | Code | |||
|---|---|---|---|---|
| BLIP2 FlanT5-XXL (Fine-tuned) | 57 | 21 | Breaking Common Sense: WHOOPS! A Vision-and-Language Benchmark of Synthetic and Compositional Images | |
| BLIP2 FlanT5-XL (Fine-tuned) | 55 | 20 | Breaking Common Sense: WHOOPS! A Vision-and-Language Benchmark of Synthetic and Compositional Images | |
| BLIP2 FlanT5-XXL (Zero-shot) | 55 | 15 | Breaking Common Sense: WHOOPS! A Vision-and-Language Benchmark of Synthetic and Compositional Images | |
| BLIP Large | 39 | 6 | Breaking Common Sense: WHOOPS! A Vision-and-Language Benchmark of Synthetic and Compositional Images | |
| OFA Large | 38 | 8 | Breaking Common Sense: WHOOPS! A Vision-and-Language Benchmark of Synthetic and Compositional Images | |
| BLIP2 FlanT5-XXL (Text-only FT) | 24 | 4 | Breaking Common Sense: WHOOPS! A Vision-and-Language Benchmark of Synthetic and Compositional Images |
0 of 6 row(s) selected.