| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Object Detection | ODinW-13 | AP72.4 | 98 | |
| Object Detection | ODinW-35 | AP70.6 | 59 | |
| Object Detection | ODinW (test) | mAP70.7 | 41 | |
| Object Detection | ODinW 13 datasets (test) | AP70.4 | 28 | |
| Object Detection | ODinW v1 (test) | mAP71.8 | 16 | |
| Object Detection | ODinW 35 datasets (test) | Average AP32.2 | 15 | |
| Object Detection | ODinW (Object Detection in the Wild) zero-shot 13 datasets | Average mAP (zero-shot)53.4 | 13 | |
| Open-vocabulary Object Detection | ODinW 13 (test) | AP55.5 | 12 | |
| Object Detection | ODinW 314 35 (val) | APb Avg29.4 | 9 | |
| Visual Grounding | ODinW (test) | Accuracy55 | 6 | |
| Single image Grounding | ODINW | mAP41.1 | 5 | |
| Object Detection | ODinW-314 13 (val) | AP (Box) avg59.8 | 5 | |
| Interactive Object Detection | ODinW35 (test) | AP50.6 | 4 | |
| Object Detection | OdinW | mAP (Mean)17.9 | 4 |