Convolutional Neural Networks


Introduced by Howard et al. in Searching for MobileNetV3

MobileNetV3 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


Paper Code Results Date Stars


Task Papers Share
Image Classification 10 12.20%
Object Detection 9 10.98%
Quantization 5 6.10%
Classification 4 4.88%
Semantic Segmentation 4 4.88%
Bayesian Optimization 3 3.66%
Test 3 3.66%
Neural Network Compression 2 2.44%
Network Pruning 2 2.44%