Abstract
Aimed to reduce the excessive cost of neural network, this paper proposes a lightweight neural network combining dilated convolution and depthwise separable convolution. Firstly, the dilated convolution is used to expand the receptive field during the convolution process while maintaining the number of convolution parameters, which can extract more high-level global semantic features and improve the classification accuracy of the network. Second, the use of the depthwise separable convolution reduces the network parameters and computational complexity in convolution operations. The experimental results on the CIFAR-10 dataset show that the proposed method improves the classification accuracy of the network while effectively compressing the network size.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Krizhevsky, A., Sutskever, I., Geoffrey, E.H.: ImageNet classification with deep convolutional neural networks (2012). http://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. Comput. Sci. (2014)
Szegedy, C., et al.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–9 (2015)
He, K., Zhang, X., Ren, S., Sun, J.: Identity mappings in deep residual networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 630–645. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46493-0_38
Xie, S., Girshick, R., Dollar, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks, pp. 1–6. arXiv preprint arXiv:1611.05431 (2016)
Iandola, F.N., Han, S., Moskewicz, M.W., Ashraf, K., Dally, W.J., Keutzer, K.: SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5 MB model size, pp. 1–8. arXiv preprint arXiv:1602.07360 (2016)
Ghemawat, S., Gobioff, H., Leung, S.T.: The Google file system. ACM SIGOPS Oper. Syst. Rev. 37(5), 29–43 (2003)
Chang, F., Dean, J., Ghemawat, S., et al.: Bigtable: a distributed storage system for structured data. ACM Trans. Comput. Syst. (TOCS). 26(2), 4–5 (2008)
Dean, J., Ghemawat, S.: MapReduce: simplified data processing on large clusters. Commun. ACM 51(1), 107–113 (2008)
Chollet, F.: Xception: deep learning with depthwise separable convolutions, p. 1. arXiv preprint arXiv:1610.02357v2 (2016)
Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks, pp. 1–7. arXiv preprint arXiv:1709.01507 (2017)
Zhang, X., Zhou, X., Lin, M., Sun, J.: ShuffleNet: an extremely efficient convolutional neural network for mobile devices. arXiv preprint arXiv:1707.01083 (2017)
Howard, A.G., et al.: MobileNets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)
Han, S., Mao, H., Dally, W.J.: Deep compression: compressing deep neural networks with pruning quantization and Huffman coding. arXiv preprint arXiv:1510.00149v5 (2016)
Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift, pp. 3–5. arXiv preprint arXiv:1502.03167 (2015)
Krizhevsky, A., Sutskever, I., Geoffrey, E.H.: ImageNet classification with deep convolutional neural networks. In: NIPS (2012)
Hu, H., Peng, R., Tai, Y.W., et al.: Network trimming: a data-driven neuron pruning approach towards efficient deep architectures. In: Proceedings of the International Conference on Learning and Representation (ICLR), pp. 214–222. IEEE (2017)
Qiu, J., et al.: Going deeper with embedded FPGA platform for convolutional neural network. In: ACM International Symposium on FPGA (2016)
Wu, J., Leng, C., Wang, Y., Hu, Q., Cheng, J.: Quantized convolutional neural networks for mobile devices, pp. 1–2. arXiv preprint arXiv:1512.06473 (2015)
Acknowledgement
This work is supported in part by the National Nature Science Foundation of China (No. 61304205, 61502240), Natural Science Foundation of Jiangsu Province (BK20191401), and Innovation and Entrepreneurship Training Project of College Students (201910300050Z, 201910300222).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering
About this paper
Cite this paper
Sun, W., Zhou, X., Zhang, X., He, X. (2020). A Lightweight Neural Network Combining Dilated Convolution and Depthwise Separable Convolution. In: Zhang, X., Liu, G., Qiu, M., Xiang, W., Huang, T. (eds) Cloud Computing, Smart Grid and Innovative Frontiers in Telecommunications. CloudComp SmartGift 2019 2019. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, vol 322. Springer, Cham. https://doi.org/10.1007/978-3-030-48513-9_17
Download citation
DOI: https://doi.org/10.1007/978-3-030-48513-9_17
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-48512-2
Online ISBN: 978-3-030-48513-9
eBook Packages: Computer ScienceComputer Science (R0)