| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Instance Segmentation | NWPU VHR-10 (test) | mIoU83.41 | 48 | |
| Object Detection | NWPU VHR (10-Split) | AP83.6 | 28 | |
| Object Detection | NWPU VHR-10 (test) | mAP95.01 | 26 | |
| Region-level Classification | NWPU-VHR-10 | Top-1 Accuracy93.75 | 21 | |
| Instance Segmentation | NWPU VHR-10 | APmask67.8 | 18 | |
| Visual Grounding | NWPU-VHR-10 (test) | mIoU63.21 | 16 | |
| Open-Vocabulary Detection | NWPU VHR-10 (val) | mAP (IoU=0.5:0.95)26 | 13 | |
| Object Detection | NWPU VHR-10 (test) | mAP (3-shot)63.9 | 13 | |
| Object Counting | NWPU-VHR | Accuracy79 | 11 | |
| Horizontal Bounding Box Object Detection | NWPU VHR-10 | mAP91.75 | 10 | |
| Referred Object Detection | NWPU VHR-10 (test) | AP (Small)14.6 | 9 | |
| Visual Grounding | NWPU-VHR-10 | mIoU61.8 | 5 | |
| Grounding Description | NWPU VHR 10 (test) | IoU @0.517.07 | 4 | |
| Region Captioning | NWPU VHR 10 | R-172.14 | 4 | |
| Object Detection | NWPU VHR-10 | mAP88.3 | 2 | |
| Grounding Description | NWPU VHR 10 | IoU @0.5- | 0 |