Meme Classification On Hateful Memes
評価指標
Accuracy
ROC-AUC
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 | ROC-AUC |
|---|---|---|
| improved-fine-tuning-of-large-multimodal-1 | 0.821 | 0.911 |
| flamingo-a-visual-language-model-for-few-shot-1 | - | 0.700 |
| vilio-state-of-the-art-visio-linguistic | 0.695 | 0.825 |
| learning-transferable-visual-models-from | - | 0.661 |
| the-hateful-memes-challenge-detecting-hate | 0.847 | 0.8265 |
| vision-models-are-more-robust-and-fair-when | - | 0.734 |
| enhance-multimodal-transformer-with-external | 0.732 | 0.845 |
| pro-cap-leveraging-a-frozen-vision-language | 0.723 | 0.809 |
| visual-program-distillation-distilling-tools | - | 0.892 |
| the-hateful-memes-challenge-detecting-hate | 0.695 | 0.754 |
| flamingo-a-visual-language-model-for-few-shot-1 | - | 0.866 |
| mapping-memes-to-words-for-multimodal-hateful | - | 0.855 |
| detecting-hate-speech-in-memes-using | 0.765 | 0.811 |
| improving-hateful-memes-detection-via | 0.788 | 0.870 |
| hate-clipper-multimodal-hateful-meme | - | 0.858 |
| improved-fine-tuning-of-large-multimodal-1 | 0.809 | 0.897 |
| improved-fine-tuning-of-large-multimodal-1 | 0.791 | 0.884 |