Open-Vocabulary Object Detection on FG-OVD (Difficulty and Attribute Metrics)
52.9Score (Hard Difficulty)DesCo + DSAA
Evaluation results
| Method | Links | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| DesCo + DSAADetector=DesCo, Enhancement Framework=DSAA2026.05 | 52.9 | 53.3 | 46.9 | 62.4 | 52.4 | 47.4 | 36.1 | 56.9 | 51 | |
| GLIP + DSAADetector=GLIP, Enhancement Framework=DSAA2026.05 | 47.1 | 52.6 | 51.1 | 57.2 | 52.2 | 45.1 | 48.6 | 55.3 | 51.1 | |
| DesCo + HA-FGOVDDetector=DesCo, Enhancement Framework=HA-FGOVD2026.05 | 45.4 | 44.5 | 38.5 | 61.8 | 47.5 | 35.9 | 21.9 | 46 | 42.6 | |
| DesCoDetector=DesCo2026.05 | 43.7 | 40 | 34.3 | 61.9 | 46.7 | 32.1 | 19.7 | 43.3 | 40.2 | |
| GLIP + HA-FGOVDDetector=GLIP, Enhancement Framework=HA-FGOVD2026.05 | 40.2 | 45.5 | 43.5 | 57.1 | 46.7 | 40.9 | 40.7 | 38.8 | 44.1 | |
| Grounding DINO + DSAADetector=Grounding DINO, Enhancement Framework=DSAA2026.05 | 38.5 | 53 | 59.2 | 63.3 | 56 | 52.3 | 46.5 | 63 | 54 | |
| GLIPDetector=GLIP2026.05 | 37.6 | 41.2 | 39.9 | 56.9 | 45.6 | 37.6 | 38.8 | 35 | 41.5 | |
| OWL-ViT(L/14)Detector=OWL-ViT(L/14)2026.05 | 26.5 | 39.3 | 44 | 65.1 | 43.8 | 44.9 | 36 | 29.2 | 41.1 | |
| OWL-ViT(B/16)Detector=OWL-ViT(B/16)2026.05 | 26.2 | 39.8 | 38.4 | 53.9 | 45.3 | 37.3 | 26.6 | 34.1 | 37.7 | |
| OWLv2(L/14)Detector=OWLv2(L/14)2026.05 | 25.4 | 41.2 | 42.8 | 63.2 | 53.3 | 36.9 | 23.3 | 12.2 | 37.3 | |
| OWLv2(B/16)Detector=OWLv2(B/16)2026.05 | 25.3 | 38.5 | 40 | 52.9 | 45.1 | 33.5 | 19.2 | 28.5 | 35.4 | |
| ViLDDetector=ViLD2026.05 | 22.1 | 31.6 | 39.9 | 56.6 | 43.2 | 34.9 | 24.5 | 30.1 | 35.9 | |
| Grounding DINO + HA-FGOVDDetector=Grounding DINO, Enhancement Framework=HA-FGOVD2026.05 | 19.2 | 32.3 | 34 | 62.2 | 41.5 | 33 | 32.1 | 29.2 | 35.4 | |
| Grounding DINODetector=Grounding DINO2026.05 | 17 | 28.4 | 31 | 62.5 | 41.4 | 30.3 | 31 | 26.2 | 33.5 | |
| CORADetector=CORA2026.05 | 13.8 | 20 | 20.4 | 35.1 | 25 | 19.3 | 22 | 27.9 | 22.9 | |
| DeticDetector=Detic2026.05 | 11.5 | 18.6 | 18.8 | 69.7 | 21.5 | 38.8 | 30.3 | 24.8 | 29.3 |