| object-detection-on-coco-minival | CP-DETR-L Swin-L(Fine tuning separately in COCO) | – | box AP: 64.1 |
| object-detection-on-lvis-v1-0-minival | CP-DETR-L Swin-L(with chunk) | – | box AP: 69.2 |
| object-detection-on-odinw-full-shot-13-tasks | CP-DETR-L(only optimize prompt) | – | AP: 73.1 |
| zero-shot-object-detection-on-lvis-v1-0 | CP-DETR-Pro(without LVIS data) | – | AP: 58.2 |
| zero-shot-object-detection-on-lvis-v1-0-val | CP-DETR-Pro(without LVIS data) | – | AP: 51.6 |
| zero-shot-object-detection-on-mscoco | CP-DETR-Pro((without COCO data)) | – | AP: 55.4 |
| zero-shot-object-detection-on-odinw | CP-DETR-L Swin-L | – | Average Score: 32.2 |