Convolutional Neural Networks
Darknet-53
Introduced by Redmon et al. in YOLOv3: An Incremental ImprovementDarknet-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 Improvement
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Object Detection | 139 | 33.10% |
| Real-Time Object Detection | 22 | 5.24% |
| Autonomous Driving | 16 | 3.81% |
| Semantic Segmentation | 12 | 2.86% |
| Image Classification | 10 | 2.38% |
| Classification | 9 | 2.14% |
| Object Tracking | 7 | 1.67% |
| Instance Segmentation | 7 | 1.67% |
| General Classification | 7 | 1.67% |
1x1 Convolution
Batch Normalization
Convolution
Global Average Pooling
Residual Connection
Softmax
