One-Stage Object Detection Models
YOLOv2
Introduced by Redmon et al. in YOLO9000: Better, Faster, StrongerYOLOv2, or YOLO9000, is a single-stage real-time object detection model. It improves upon YOLOv1 in several ways, including the use of Darknet-19 as a backbone, batch normalization, use of a high-resolution classifier, and the use of anchor boxes to predict bounding boxes, and more.
Source: YOLO9000: Better, Faster, Stronger
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Object Detection | 29 | 36.25% |
| Real-Time Object Detection | 5 | 6.25% |
| License Plate Recognition | 3 | 3.75% |
| Quantization | 3 | 3.75% |
| Image Classification | 3 | 3.75% |
| General Classification | 3 | 3.75% |
| Human Detection | 2 | 2.50% |
| 3D Object Detection | 2 | 2.50% |
| License Plate Detection | 2 | 2.50% |
Darknet-19
