Convolutional Neural Networks
CSPDarknet53
Introduced by Bochkovskiy et al. in YOLOv4: Optimal Speed and Accuracy of Object DetectionCSPDarknet53 is a convolutional neural network and backbone for object detection that uses DarkNet-53. It employs a CSPNet strategy to partition the feature map of the base layer into two parts and then merges them through a cross-stage hierarchy. The use of a split and merge strategy allows for more gradient flow through the network.
This CNN is used as the backbone for YOLOv4.
Source: YOLOv4: Optimal Speed and Accuracy of Object Detection
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Object Detection | 56 | 31.11% |
| Real-Time Object Detection | 14 | 7.78% |
| Autonomous Driving | 6 | 3.33% |
| Object Tracking | 5 | 2.78% |
| 2D object detection | 5 | 2.78% |
| Semantic Segmentation | 5 | 2.78% |
| Image Classification | 4 | 2.22% |
| Multi-Object Tracking | 4 | 2.22% |
| Domain Adaptation | 3 | 1.67% |
Darknet-53
