| cross-domain-few-shot-object-detection-on | DE-ViT-FT | #4 | mAP: 49.2 |
| cross-domain-few-shot-object-detection-on | DE-ViT(w/o FT) | #12 | mAP: 9.2 |
| cross-domain-few-shot-object-detection-on-1 | DE-ViT-FT | #5 | mAP: 40.8 |
| cross-domain-few-shot-object-detection-on-1 | DE-ViT(w/o FT) | #10 | mAP: 11.0 |
| cross-domain-few-shot-object-detection-on-2 | DE-ViT-FT | #5 | mAP: 25.6 |
| cross-domain-few-shot-object-detection-on-2 | DE-ViT(w/o FT) | #11 | mAP: 8.4 |
| cross-domain-few-shot-object-detection-on-3 | DE-ViT-FT | #6 | mAP: 21.3 |
| cross-domain-few-shot-object-detection-on-3 | DE-ViT(w/o FT) | #9 | mAP: 2.1 |
| cross-domain-few-shot-object-detection-on-4 | DE-ViT-FT | #11 | mAP: 5.4 |
| cross-domain-few-shot-object-detection-on-4 | DE-ViT(w/o FT) | #12 | mAP: 3.1 |
| cross-domain-few-shot-object-detection-on-neu | DE-ViT-FT | #6 | mAP: 8.8 |
| cross-domain-few-shot-object-detection-on-neu | DE-ViT(w/o FT) | #9 | mAP: 1.8 |
| few-shot-object-detection-on-ms-coco-10-shot | DE-ViT | #3 | AP: 34.0 |
| few-shot-object-detection-on-ms-coco-30-shot | DE-ViT | #3 | AP: 34 |
| one-shot-object-detection-on-coco | DE-ViT | #2 | AP 0.5: 28.4 |
| open-vocabulary-object-detection-on-lvis-v1-0 | DE-ViT | #7 | AP novel-LVIS base training: 34.3 |
| open-vocabulary-object-detection-on-mscoco | DE-ViT | #2 | AP 0.5: 50 |