Object Detection on LVIS open scene generalization
27.8APcRTVPNet (YOLOv11s)
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| RTVPNet (YOLOv11s)Data=O365,GlodG, Param=732026.06 | 27.8 | 29.4 | 22.8 | 31.9 | |
| Mamba-YOLO-World-SData=O365,GlodG, Param=782026.06 | 27 | 27.7 | 19.5 | 29.9 | |
| YOLO-World-SData=O365,GlodG, Param=772026.06 | 23.6 | 26.2 | 19.1 | 29.8 | |
| RTVP (Our Previous work)Data=O365,GlodG, Param=1312026.06 | 23.4 | 26.8 | 19.5 | 30.7 | |
| RTVPNet (YOLOv11s)Data=O365, Param=732026.06 | 23.2 | 25.2 | 18.3 | 28.5 | |
| RTVP (Previous work)Data=O365, Param=131M2026.06 | 22.4 | 24.1 | 17.3 | 27.9 | |
| YOLO-World-v1Data=O365, Param=77M2026.06 | 21.1 | 23.5 | 16.2 | 27 | |
| ViLDData=O365, Param=-2026.06 | 20 | — | — | 28.3 | |
| Grounding-Dino-TData=O365,GlodG, Param=1732026.06 | 19.6 | 25.6 | 14.4 | 32.2 | |
| GLIP-TData=O365,GlodG, Param=2322026.06 | 19.5 | 24.9 | 17.7 | 31 | |
| GLIP-TData=O365, Param=232M2026.06 | 12.8 | 17.8 | 13.5 | 22.2 |