Convolutional Neural Networks
ShuffleNet
Introduced by Zhang et al. in ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile DevicesShuffleNet is a convolutional neural network designed specially for mobile devices with very limited computing power. The architecture utilizes two new operations, pointwise group convolution and channel shuffle, to reduce computation cost while maintaining accuracy.
Source: ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Semantic Segmentation | 5 | 9.80% |
| Model Compression | 4 | 7.84% |
| Image Classification | 4 | 7.84% |
| Object Detection | 4 | 7.84% |
| Real-Time Semantic Segmentation | 3 | 5.88% |
| Network Pruning | 2 | 3.92% |
| Rain Removal | 2 | 3.92% |
| Single Image Deraining | 2 | 3.92% |
| Quantization | 2 | 3.92% |
Convolution
Dense Connections
Global Average Pooling
Max Pooling
ShuffleNet Block
Softmax
