| Paper | Code | Precision | Recall | F1 | Accuracy | mAP | ModelName | ReleaseDate |
|---|---|---|---|---|---|---|---|---|
| TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias | ✓ Link | 88.3 | 78.0 | 82.8 | 88.6 | 93.7 | TTD (w/ fine-tuning) | 2024-03-30 |
| TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias | ✓ Link | 82.9 | 74.5 | 78.5 | 91.0 | 90.3 | TTD (w/o fine-tuning) | 2024-03-30 |
| Qwen Technical Report | ✓ Link | 69.3 | 56.2 | 62.1 | 80.9 | Qwen-72B | 2023-09-28 | |
| NLTK: The Natural Language Toolkit | ✓ Link | 59.8 | 83.7 | 69.8 | 79.6 | NLTK | 2002-05-17 | |
| []() | 52.7 | 70.7 | 60.4 | 75.9 | Vicuna-33B | |||
| []() | 44.1 | 71.0 | 54.4 | 70.9 | Vicuna-7B |