Visual Question Answering On Vcr Q A Test
평가 지표
Accuracy
평가 결과
이 벤치마크에서 각 모델의 성능 결과
비교 표
| 모델 이름 | Accuracy |
|---|---|
| vl-bert-pre-training-of-generic-visual | 75.8 |
| multimodal-adaptive-distillation-for | 79.6 |
| uniter-learning-universal-image-text-1 | 77.3 |
| gpt4roi-instruction-tuning-large-language | 89.4 |
| visualbert-a-simple-and-performant-baseline | 71.6 |
| ernie-vil-knowledge-enhanced-vision-language | 81.6 |
| uniter-learning-universal-image-text-1 | 79.8 |
| harnessing-the-power-of-multi-task | 71.2 |
| harnessing-the-power-of-multi-task | 62 |
| unifying-vision-and-language-tasks-via-text | 75.3 |
| kvl-bert-knowledge-enhanced-visual-and | 76.4 |