Zero Shot Object Detection On Lvis V1 0
Métriques
AP
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | AP |
|---|---|
| grounding-dino-1-5-advance-the-edge-of-open | 57.7 |
| grounding-dino-1-5-advance-the-edge-of-open | 55.7 |
| multi-modal-queried-object-detection-in-the | 43.4 |
| multi-modal-queried-object-detection-in-the | 30.4 |
| grounding-dino-marrying-dino-with-grounded | 33.9 |
| multi-modal-queried-object-detection-in-the | 30.2 |
| grounded-language-image-pre-training | 37.3 |
| ov-dino-unified-open-vocabulary-detection | 40.1 |
| cp-detr-concept-prompt-guide-detr-toward | 58.2 |
| yolo-world-real-time-open-vocabulary-object | 35.4 |
| scaling-open-vocabulary-object-detection-1 | 51.3 |