Convolutional Neural Networks
Darknet-19
Introduced by Redmon et al. in YOLO9000: Better, Faster, StrongerDarknet-19 is a convolutional neural network that is used as the backbone of YOLOv2. Similar to the VGG models it mostly uses $3 \times 3$ filters and doubles the number of channels after every pooling step. Following the work on Network in Network (NIN) it uses global average pooling to make predictions as well as $1 \times 1$ filters to compress the feature representation between $3 \times 3$ convolutions. Batch Normalization is used to stabilize training, speed up convergence, and regularize the model batch.
Source: YOLO9000: Better, Faster, Stronger
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Object Detection | 29 | 38.16% |
| Real-Time Object Detection | 5 | 6.58% |
| Quantization | 3 | 3.95% |
| Image Classification | 3 | 3.95% |
| General Classification | 3 | 3.95% |
| 3D Object Detection | 3 | 3.95% |
| Human Detection | 2 | 2.63% |
| Autonomous Driving | 2 | 2.63% |
| Action Detection | 1 | 1.32% |
1x1 Convolution
Batch Normalization
Convolution
Global Average Pooling
Max Pooling
Softmax
