CSPDarknet53 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 DetectionPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Object Detection | 72 | 32.00% |
Real-Time Object Detection | 14 | 6.22% |
Autonomous Driving | 7 | 3.11% |
Semantic Segmentation | 6 | 2.67% |
Object Tracking | 6 | 2.67% |
2D Object Detection | 6 | 2.67% |
Multi-Object Tracking | 5 | 2.22% |
Instance Segmentation | 4 | 1.78% |
Multiple Object Tracking | 4 | 1.78% |