常见轻量级深度学习模型

深度学习模型参数很多（模型很大）是制约深度学习模型部署在移动端一个很大的瓶颈，最近有不少轻量级的深度学习模型提出，以下是对一些经典轻量级深度学习模型的总结：

1、Squeezenet:Alexnet-level accuracy with 50x fewer parameters and¡ 1mb model size.

arXiv preprint arXiv:1602.07360, 2016

 

2、MobileNets:Efficient Convolutional Neural Networks for Mobile Vision Applications

arXiv:1704.04861v1 [cs.CV] 17 Apr 2017

 

3、Densely ConnectedConvolutional Networks

arXiv:1608.06993v4 [cs.CV] 27 Aug 2017

 

4、Xnornet: Imagenetclassification using binary convolutional neural networks.

arXiv preprint arXiv:1603.05279, 2016

 

5、Quantized convolutionalneural networks for mobile devices

arXiv preprint arXiv:1512.06473, 2015

 

6、Xception: DeepLearning with Depthwise Separable Convolutions

arXiv:1610.02357v3 [cs.CV] 4 Apr 2017

 

7、ProjectionNet: LearningEfficient On-Device Deep Networks Using Neural Projections

arXiv:1708.00630v2 [cs.LG] 9 Aug 2017

 

8、Factorizedconvolutional neural networks

arXiv preprint arXiv:1608.04337, 2016

 

9、LearningTransferable Architectures for Scalable Image Recognition

atXiv:1707.07012v2 [cs.CV] 25 Oct 2017

 

10、Structured transformsfor small-footprint deep learning.

 

11、Deep compression:Compressing deep neural network with pruning, trained quantization and huffmancoding

 

12、Quantized neuralnetworks: Training neural networks with low precision weights and activations.

 arXivpreprint arXiv:1609.07061, 2016