Eye detection on Our dataset of real surgeries
89.54PrecisionIter-Score
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| Iter-ScoreBase Detector=P-D-DETR2026.02 | 89.54 | 91.99 | 88.71 | 62.1 | 87 | |
| Our approach (P-D-DETR)Base Detector=P-D-DETR, FPS=8.632026.02 | 88.08 | 97.06 | 87.83 | 84.57 | 95.21 | |
| Our approach (DEIM)Base Detector=DEIM [15], FPS=52.092026.02 | 86.69 | 97.46 | 87.82 | 86.7 | 95.87 | |
| P-D-DETRTraining Dataset=CrowdHuman2026.02 | 85.4 | 93.17 | 88.59 | 70.61 | 88.86 | |
| RetinaFaceTraining Dataset=WIDER FACE2026.02 | 65.96 | 38.87 | 31.78 | 8.91 | 22.62 | |
| Head-YOLOv8Training Dataset=CrowdHuman2026.02 | 25.01 | 33 | 10.99 | 10.77 | 21.86 |