Darknet-53 is a convolutional neural network that acts as a backbone for the YOLOv3 object detection approach. The improvements upon its predecessor Darknet-19 include the use of residual connections, as well as more layers.
Source: YOLOv3: An Incremental ImprovementPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Object Detection | 152 | 32.83% |
Real-Time Object Detection | 22 | 4.75% |
Autonomous Driving | 18 | 3.89% |
Semantic Segmentation | 13 | 2.81% |
Classification | 10 | 2.16% |
Image Classification | 10 | 2.16% |
Instance Segmentation | 8 | 1.73% |
Object Tracking | 8 | 1.73% |
2D Object Detection | 8 | 1.73% |