Visual Question Answering On Gqa Test Std
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 |
|---|---|
| lxmert-learning-cross-modality-encoder | 60.3 |
| gqa-a-new-dataset-for-compositional-question | 46.55 |
| language-conditioned-graph-networks-for | 56.1 |
| proto-program-guided-transformer-for-program | 65.14 |
| mdetr-modulated-detection-for-end-to-end | 62.45 |
| learning-by-abstraction-the-neural-state | 63.17 |
| gqa-a-new-dataset-for-compositional-question | 54.06 |