Abstract
Convolutional neural networks (CNNs) have achieved outstanding performance in many applications. However, as the total number of layers has increased and the model structure has become compound, the computational cost comes into question. The large models cannot operate in embedded or mobile environments where hardware resources are quite limited. To overcome these problems, there have been several attempts like reducing the depth of networks, pruning, quantization or low rank approximation. Depthwise separable convolution (DSC) was proposed to reduce computation especially in convolutional layers by separating one convolution into a spatial convolution and a pointwise convolution. In this paper, we apply DSC to the YOLO network for object detection and propose a faster version of DSC, FastDSC by replacing the pointwise convolution with general matrix multiplication. Experiments on the NVIDIA Jetson TX2 board show that FastDSC speeds up DSC for object detection.
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
Similar content being viewed by others
References
Chollet, F.: Xception: deep learning with depthwise separable convolutions. CoRR abs/1610.02357 (2016). http://arxiv.org/abs/1610.02357
Courbariaux, M., Bengio, Y., David, J.: Binaryconnect: training deep neural networks with binary weights during propagations. CoRR abs/1511.00363 (2015). http://arxiv.org/abs/1511.00363
Dahl, G.E., Sainath, T.N., Hinton, G.E.: Improving deep neural networks for LVCSR using rectified linear units and dropout (2013)
Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The pascal visual object classes (VOC) challenge. Int. J. Comput. Vis. 88(2), 303–338 (2010)
Fukushima, K.: Neocognitron: a self-organizing neural network for a mechanism of pattern recognition unaffected by shift in position. Biol. Cybern. 36(4), 193–202 (1980)
Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS 2010). Society for Artificial Intelligence and Statistics (2010)
Hinton, G., et al.: Deep neural networks for acoustic modeling in speech recognition. IEEE Signal Process. Mag. 29, 82–97 (2012)
Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531v1 (2015)
Howard, A.G., et al,: Mobilenets: efficient convolutional neural networks for mobile vision applications. CoRR abs/1704.04861 (2017). http://arxiv.org/abs/1704.04861
Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. CoRR abs/1502.03167 (2015). http://arxiv.org/abs/1502.03167
Kim, Y., Park, E., Yoo, S., Choi, T., Yang, L., Shin, D.: Compression of deep convolutional neural networks for fast and low power mobile applications. CoRR abs/1511.06530 (2015). http://arxiv.org/abs/1511.06530
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)
LeCun, Y., Bengio, Y., Hinton, G.E.: Deep learning. Nature 521(7553), 436–444 (2015)
LeCun, Y., Cortes, C.: MNIST handwritten digit database (2010). http://yann.lecun.com/exdb/mnist/
Nair, V., Hinton, G.E.: Rectified linear units improve restricted Boltzmann machines (2010)
Redmon, J., Farhadi, A.: YOLO9000: better, faster, stronger. CoRR abs/1612.08242 (2016). http://arxiv.org/abs/1612.08242
Romero, A., Ballas, N., Kahou, S.E., Chassang, A., Gatta, C., Bengio, Y.: Fitnets: hints for thin deep nets. CoRR abs/1412.6550 (2014). http://arxiv.org/abs/1412.6550
Schmidhuber, J.: Deep learning in neural networks: an overview. Neural Netw. 61, 85–117 (2015)
Zhang, X., Zhou, X., Lin, M., Sun, J.: ShuffleNet: an extremely efficient convolutional neural network for mobile devices. CoRR abs/1707.01083 (2017). http://arxiv.org/abs/1707.01083
Acknowledgement
This work was partly supported by Institute for Information & communications Technology Promotion(IITP) grant funded by the Korea government(MSIT) (No. 2018-0-00749,Development of virtual network management technology based on artificial intelligence) and the National Program for Excellence in Software funded by the Ministry of Science, ICT and Future Planning, Republic of Korea (2017-0-00130).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Yoo, B., Choi, Y., Choi, H. (2018). Fast Depthwise Separable Convolution for Embedded Systems. In: Cheng, L., Leung, A., Ozawa, S. (eds) Neural Information Processing. ICONIP 2018. Lecture Notes in Computer Science(), vol 11307. Springer, Cham. https://doi.org/10.1007/978-3-030-04239-4_59
Download citation
DOI: https://doi.org/10.1007/978-3-030-04239-4_59
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-04238-7
Online ISBN: 978-3-030-04239-4
eBook Packages: Computer ScienceComputer Science (R0)