Convolutional Neural Networks
MobileNetV1
Introduced by Howard et al. in MobileNets: Efficient Convolutional Neural Networks for Mobile Vision ApplicationsMobileNet is a type of convolutional neural network designed for mobile and embedded vision applications. They are based on a streamlined architecture that uses depthwise separable convolutions to build lightweight deep neural networks that can have low latency for mobile and embedded devices.
Source: MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Image Classification | 15 | 12.40% |
| Object Detection | 15 | 12.40% |
| Quantization | 12 | 9.92% |
| Network Pruning | 6 | 4.96% |
| Model Compression | 5 | 4.13% |
| Computational Efficiency | 4 | 3.31% |
| Semantic Segmentation | 4 | 3.31% |
| General Classification | 4 | 3.31% |
| Deep Learning | 3 | 2.48% |
1x1 Convolution
Batch Normalization
Convolution
Dense Connections
Depthwise Separable Convolution
Global Average Pooling
ReLU
Softmax
