Meme Classification
Meme classification refers to the task of classifying internet memes.
Papers
No papers found.
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | RA-HMD (Qwen2-VL-7B) | ROC-AUC | 0.91 | — | Unverified |
| 2 | RA-HMD (LLaVA-1.5-7B) | ROC-AUC | 0.9 | — | Unverified |
| 3 | PaLI-X-VPD | ROC-AUC | 0.89 | — | Unverified |
| 4 | RA-HMD (Qwen2-VL-2B) | ROC-AUC | 0.88 | — | Unverified |
| 5 | RGCL (CLIP) | ROC-AUC | 0.87 | — | Unverified |
| 6 | Flamingo (fine-tuned) | ROC-AUC | 0.87 | — | Unverified |
| 7 | Hate-CLIPper - Align | ROC-AUC | 0.86 | — | Unverified |
| 8 | ISSUES | ROC-AUC | 0.86 | — | Unverified |
| 9 | Ron Zhu | ROC-AUC | 0.85 | — | Unverified |
| 10 | Human | ROC-AUC | 0.83 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | RA-HMD (Qwen2-VL-7B) | Accuracy | 71.1 | — | Unverified |
| 2 | RGCL | Accuracy | 67.1 | — | Unverified |
| 3 | HateCLIPper | Accuracy | 62.4 | — | Unverified |
| 4 | CLIP | Accuracy | 62.4 | — | Unverified |
| 5 | MultiOFF | F1 | 50 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | Hate-CLIPper | Micro-F1 | 0.59 | — | Unverified |
| 2 | UVCE-IIITT | Micro-F1 | 0.47 | — | Unverified |