| Benchmark | Model | Rank | Results |
|---|---|---|---|
| object-detection-on-peopleart | PVT (Pyramid Vision Transformer) | – | mAP: 46.5mAP@0.5: 76.0mAP@0.75: 48.4 |
| object-detection-on-peopleart | PVT (Pyramid Vision Transformer; trained on PeopleArt and PopArt) | – | mAP: 49.7mAP@0.5: 80.5mAP@0.75: 51.8 |
| object-detection-on-peopleart | TOOD (Task-aligned One-stage Object Detection) | – | mAP: 46.1mAP@0.5: 75.0mAP@0.75: 49.0 |
| object-detection-on-peopleart | TOOD (Task-aligned One-stage Object Detection; trained on PeopleArt and PoPArt) | – | mAP: 47.8mAP@0.5: 78.0mAP@0.75: 49.9 |