Image Captioning On Whoops
Metrics
BLEU-4
CIDEr
Results
Performance results of various models on this benchmark
Model Name | BLEU-4 | CIDEr | Paper Title | Repository |
|---|---|---|---|---|
| OFA Large | 0 | 0 | Breaking Common Sense: WHOOPS! A Vision-and-Language Benchmark of Synthetic and Compositional Images | - |
| BLIP2 FlanT5-XXL (Fine-tuned) | 42 | 177 | Breaking Common Sense: WHOOPS! A Vision-and-Language Benchmark of Synthetic and Compositional Images | - |
| CoCa ViT-L-14 MSCOCO | 25 | 102 | Breaking Common Sense: WHOOPS! A Vision-and-Language Benchmark of Synthetic and Compositional Images | - |
| BLIP2 FlanT5-XXL (Zero-Shot) | 31 | 120 | Breaking Common Sense: WHOOPS! A Vision-and-Language Benchmark of Synthetic and Compositional Images | - |
| BLIP Large | 13 | 65 | Breaking Common Sense: WHOOPS! A Vision-and-Language Benchmark of Synthetic and Compositional Images | - |
| BLIP2 FlanT5-XL (Fine-tuned) | 41 | 174 | Breaking Common Sense: WHOOPS! A Vision-and-Language Benchmark of Synthetic and Compositional Images | - |
0 of 6 row(s) selected.