An Enhanced Hybrid MobileNet

Complicated and deep neural network models can achieve high accuracy for image recognition. However, they require a huge amount of computations and model parameters, which are not suitable for mobile and embedded devices. Therefore, MobileNet was proposed, which can reduce the number of parameters and computational cost dramatically. The main idea of MobileNet is to use a depthwise separable convolution. Two hyper-parameters, a width multiplier and a resolution multiplier are used to the trade-off between the accuracy and the latency. In this paper, we propose a new architecture to improve the MobileNet. Instead of using the resolution multiplier, we use a depth multiplier and combine with either Fractional Max Pooling or the max pooling. Experimental results on CIFAR database show that the proposed architecture can reduce the amount of computational cost and increase the accuracy simultaneously 1.This work is partly supported by Ministry of Science and Technology, R.O.C. under Contract No. MOST 106-2221-E-003-011.

[1]  Martín Abadi,et al.  TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems , 2016, ArXiv.

[2]  Hassan Foroosh,et al.  Factorized Convolutional Neural Networks , 2016, 2017 IEEE International Conference on Computer Vision Workshops (ICCVW).

[3]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[4]  Benjamin Graham,et al.  Fractional Max-Pooling , 2014, ArXiv.

[5]  Ngoc Thang Vu,et al.  Densely Connected Convolutional Networks for Speech Recognition , 2018, ITG Symposium on Speech Communication.

[6]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[7]  Sergey Ioffe,et al.  Rethinking the Inception Architecture for Computer Vision , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  Ali Farhadi,et al.  XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks , 2016, ECCV.

[9]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[10]  Bo Chen,et al.  MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications , 2017, ArXiv.

[11]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  Forrest N. Iandola,et al.  SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <1MB model size , 2016, ArXiv.

[13]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[14]  Eugenio Culurciello,et al.  Flattened Convolutional Neural Networks for Feedforward Acceleration , 2014, ICLR.