Object Detection on COCO (val) (APM/APL Reporting)
71.2APMGrounding DINO-T
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Grounding DINO-TBackbone=Swin-T, Training Datasets=COCO, O365, GoldG, Cap4M, OpenImage, ODinW-35, RefCOCO, Dataset Volume=1858K + 155K, Fine-tuned=true2023.10 | 71.2 | 83.4 | |
| X-Pose-TBackbone=Swin-T, Training Datasets=COCO, Human-Art, AP-10K, APT-36K, Dataset Volume=155K, Prompting=Textual2023.10 | 71.1 | 80.2 | |
| X-Pose-VBackbone=Swin-T, Training Datasets=COCO, Human-Art, AP-10K, APT-36K, Dataset Volume=155K, Prompting=Visual2023.10 | 71.1 | 80.3 | |
| Grounding DINO-TBackbone=Swin-T, Training Datasets=O365, GoldG, Cap4M, Dataset Volume=1858K, Fine-tuned=false2023.10 | 70.8 | 82 | |
| Grounding DINO-BBackbone=Swin-B, Training Datasets=O365, GoldG, Cap4M, Dataset Volume=1858K, Fine-tuned=false2023.10 | 69.7 | 79.5 |