Hateful Meme Classification On Harm P
Metriken
Accuracy
F1
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Vergleichstabelle
| Modellname | Accuracy | F1 |
|---|---|---|
| hate-clipper-multimodal-hateful-meme | 87.6 | 86.9 |
| improving-hateful-memes-detection-via | 89.9 | 89.5 |
| improved-fine-tuning-of-large-multimodal-1 | 91.6 | 91.1 |
| towards-explainable-harmful-meme-detection | 90.7 | 90.7 |
| learning-transferable-visual-models-from | 80.6 | 80.3 |