Abstract
Deep convolutional neural networks (CNNs) currently demonstrate the state-of-the-art performance in several domains. However, a large amount of memory and computing resources are required in the commonly used CNN models, posing challenges in training as well as deploying, especially on those devices with limited computational resources. Inspired by the recent advancement of random tensor decomposition, we introduce a Hierarchical Framework for Fast and Robust Compression (HFFRC), which significantly reduces the number of parameters needed to represent a convolution layer via a fast low-rank Tucker decomposition algorithm, while preserving its expressive power. In the merit of randomized algorithm, the proposed compression framework is robust to noises in parameters. In addition, it is a general framework that any tensor decomposition method can be easily adopted. The efficiency and effectiveness of the proposed approach have been demonstrated via comprehensive experiments conducted on the benchmarks CIFAR-10 and CIFAR-100 image classification datasets.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Astrid, M., Lee, S.I.: CP-decomposition with tensor power method for convolutional neural networks compression. In: 2017 IEEE International Conference on Big Data and Smart Computing, pp. 115–118. IEEE (2017). https://doi.org/10.1109/BIGCOMP.2017.7881725
Ba, J., Caruana, R.: Do deep nets really need to be deep? In: Advances in Neural Information Processing Systems, pp. 2654–2662 (2014)
Balevi, E., Andrews, J.G.: Autoencoder-based error correction coding for one-bit quantization. IEEE Trans. Commun. (2020). https://doi.org/10.1109/tcomm.2020.2977280
Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248–255. IEEE (2009). https://doi.org/10.1109/CVPR.2009.5206848
Denil, M., Shakibi, B., Dinh, L., Ranzato, M., De Freitas, N.: Predicting parameters in deep learning. In: Advances in Neural Information Processing Systems, pp. 2148–2156 (2013). https://doi.org/10.14288/1.0165555
Erichson, N.B., Manohar, K., Brunton, S.L., Kutz, J.N.: Randomized CP tensor decomposition. arXiv preprint arXiv:1703.09074 (2017)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016). https://doi.org/10.1109/CVPR.2016.90
He, Y., Zhang, X., Sun, J.: Channel pruning for accelerating very deep neural networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1389–1397 (2017). https://doi.org/10.1109/iccv.2017.155
Kim, Y.D., Park, E., Yoo, S., Choi, T., Yang, L., Shin, D.: Compression of deep convolutional neural networks for fast and low power mobile applications. arXiv preprint arXiv:1511.06530 (2015)
Krizhevsky, A., et al.: Learning multiple layers of features from tiny images. Technical report, Citeseer (2009)
Lebedev, V., Ganin, Y., Rakhuba, M., Oseledets, I., Lempitsky, V.: Speeding-up convolutional neural networks using fine-tuned CP-decomposition. arXiv preprint arXiv:1412.6553 (2014)
Li, H., Kadav, A., Durdanovic, I., Samet, H., Graf, H.P.: Pruning filters for efficient convnets. arXiv preprint arXiv:1608.08710 (2016)
Liu, W., Wen, Y., Yu, Z., Li, M., Raj, B., Song, L.: Sphereface: deep hypersphere embedding for face recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 212–220 (2017). https://doi.org/10.1109/cvpr.2017.713
Luo, J.H., Wu, J., Lin, W.: Thinet: a filter level pruning method for deep neural network compression. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5058–5066 (2017). https://doi.org/10.1109/ICCV.2017.541
Ma, Y., et al.: A unified approximation framework for compressing and accelerating deep neural networks. In: 2019 IEEE 31st International Conference on Tools with Artificial Intelligence (ICTAI), pp. 376–383. IEEE (2019). https://doi.org/10.1109/ICTAI.2019.00060
Minster, R., Saibaba, A.K., Kilmer, M.E.: Randomized algorithms for low-rank tensor decompositions in the tucker format. SIAM J. Math. Data Sci. 2(1), 189–215 (2020). https://doi.org/10.1137/19m1261043
Molchanov, P., Mallya, A., Tyree, S., Frosio, I., Kautz, J.: Importance estimation for neural network pruning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 11264–11272 (2019). https://doi.org/10.1109/CVPR.2019.01152
Nakajima, S., Sugiyama, M., Babacan, S.D., Tomioka, R.: Global analytic solution of fully-observed variational bayesian matrix factorization. J. Mach. Learn. Res. 14, 1–37 (2013). https://doi.org/10.1016/j.imavis.2012.11.001
Redmon, J., Farhadi, A.: Yolov3: an incremental improvement. arXiv preprint arXiv:1804.02767 (2018)
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: Mobilenetv 2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4510–4520 (2018). https://doi.org/10.1109/CVPR.2018.00474
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
Tan, M., Le, Q.V.: Efficientnet: rethinking model scaling for convolutional neural networks. arXiv preprint arXiv:1905.11946 (2019)
Tjandra, A., Sakti, S., Nakamura, S.: Compressing recurrent neural network with tensor train. In: 2017 International Joint Conference on Neural Networks, pp. 4451–4458. IEEE (2017). https://doi.org/10.1109/ijcnn.2017.7966420
Wang, F., et al.: Residual attention network for image classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3156–3164 (2017). https://doi.org/10.1109/CVPR.2017.683
Wang, K., Liu, Z., Lin, Y., Lin, J., Han, S.: Haq: hardware-aware automated quantization with mixed precision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8612–8620 (2019). https://doi.org/10.1109/CVPR.2019.00881
Wang, W., Sun, Y., Eriksson, B., Wang, W., Aggarwal, V.: Wide compression: tensor ring nets. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9329–9338 (2018). https://doi.org/10.1109/cvpr.2018.00972
Wang, Y., Tung, H.Y., Smola, A.J., Anandkumar, A.: Fast and guaranteed tensor decomposition via sketching. In: Advances in Neural Information Processing Systems, pp. 991–999 (2015)
Ye, J., et al.: Learning compact recurrent neural networks with block-term tensor decomposition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9378–9387 (2018). https://doi.org/10.1109/cvpr.2018.00977
Yuan, L., Li, C., Cao, J., Zhao, Q.: Randomized tensor ring decomposition and its application to large-scale data reconstruction. In: IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 2127–2131 (2019). https://doi.org/10.1109/ICASSP.2019.8682197
Zhou, G., Cichocki, A., Xie, S.: Decomposition of big tensors with low multilinear rank. arXiv preprint arXiv:1412.1885 (2014)
Acknowledgements
This work was supported in part by the National Natural Science Foundation of China under Grant 61732011 and Grant 61702358, in part by the Beijing Natural Science Foundation under Grant Z180006, in part by the Key Scientific and Technological Support Project of Tianjin Key Research and Development Program under Grant 18YFZCGX00390, and in part by the Tianjin Science and Technology Plan Project under Grant 19ZXZNGX00050.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Wen, J., Yang, L., Shen, C. (2020). Fast and Robust Compression of Deep Convolutional Neural Networks. In: Farkaš, I., Masulli, P., Wermter, S. (eds) Artificial Neural Networks and Machine Learning – ICANN 2020. ICANN 2020. Lecture Notes in Computer Science(), vol 12397. Springer, Cham. https://doi.org/10.1007/978-3-030-61616-8_5
Download citation
DOI: https://doi.org/10.1007/978-3-030-61616-8_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-61615-1
Online ISBN: 978-3-030-61616-8
eBook Packages: Computer ScienceComputer Science (R0)