Visual Question Answering On Ok Vqa
評価指標
Accuracy
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
比較表
| モデル名 | Accuracy |
|---|---|
| palm-e-an-embodied-multimodal-language-model | 66.1 |
| an-empirical-study-of-gpt-3-for-few-shot | 48.0 |
| language-models-are-general-purpose | 11.4 |
| revive-regional-visual-representation-matters | 58.0 |
| a-simple-baseline-for-knowledge-based-visual | 61.2 |
| prompting-large-language-models-with-answer | 62.5 |
| plug-and-play-vqa-zero-shot-vqa-by-conjoining | 35.9 |
| retrieval-augmented-visual-question-answering | 51.22 |
| vlc-bert-visual-question-answering-with | 43.1 |
| blip-2-bootstrapping-language-image-pre | 39.4 |
| multimodal-few-shot-learning-with-frozen | 5.9 |
| lako-knowledge-driven-visual-question | 42.03 |
| implicit-differentiable-outlier-detection | 52.4 |
| a-good-prompt-is-worth-millions-of-parameters | 16.5 |
| blip-2-bootstrapping-language-image-pre | 45.9 |
| lako-knowledge-driven-visual-question | 47.01 |
| enabling-multimodal-generation-on-clip-via | 10.5 |
| fine-grained-late-interaction-multi-modal-1 | 62.08 |
| blip-2-bootstrapping-language-image-pre | 31.7 |
| flamingo-a-visual-language-model-for-few-shot-1 | 41.2 |
| pali-a-jointly-scaled-multilingual-language | 64.5 |
| lyrics-boosting-fine-grained-language-vision | 58.2 |
| revive-regional-visual-representation-matters | 56.6 |
| flamingo-a-visual-language-model-for-few-shot-1 | 44.7 |
| blip-2-bootstrapping-language-image-pre | 40.7 |
| visual-program-distillation-distilling-tools | 66.8 |
| promptcap-prompt-guided-task-aware-image | 60.4 |
| pali-x-on-scaling-up-a-multilingual-vision | 66.1 |
| differentiable-outlier-detection-enable | 52.4 |
| fine-grained-late-interaction-multi-modal-1 | 54.85 |
| retrieval-augmented-visual-question-answering | 54.48 |
| reveal-retrieval-augmented-visual-language | 59.1 |
| blip-2-bootstrapping-language-image-pre | 30.2 |
| transform-retrieve-generate-natural-language | 50.50 |
| blip-2-bootstrapping-language-image-pre | 36.4 |
| hydra-a-hyper-agent-for-dynamic-compositional | 48.6 |
| flamingo-a-visual-language-model-for-few-shot-1 | 50.6 |