Convolutional Neural Networks
MobileNetV3
Introduced by Howard et al. in Searching for MobileNetV3MobileNetV3 is a convolutional neural network that is tuned to mobile phone CPUs through a combination of hardware-aware network architecture search (NAS) complemented by the NetAdapt algorithm, and then subsequently improved through novel architecture advances. Advances include (1) complementary search techniques, (2) new efficient versions of nonlinearities practical for the mobile setting, (3) new efficient network design.
The network design includes the use of a hard swish activation and squeeze-and-excitation modules in the MBConv blocks.
Source: Searching for MobileNetV3
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Image Classification | 10 | 12.35% |
| Object Detection | 9 | 11.11% |
| Classification | 5 | 6.17% |
| Quantization | 5 | 6.17% |
| Semantic Segmentation | 4 | 4.94% |
| Bayesian Optimization | 3 | 3.70% |
| Neural Network Compression | 2 | 2.47% |
| Network Pruning | 2 | 2.47% |
| Reinforcement Learning (RL) | 2 | 2.47% |
1x1 Convolution
Convolution
Dropout
Global Average Pooling
Hard Swish
Inverted Residual Block
ReLU
Squeeze-and-Excitation Block
