Abstract
The convolutional neural network (CNN) has gained widespread adoption in computer vision (CV) applications in recent years. However, the high computational complexity of spatial (conventional) CNNs makes real-time deployment in CV applications difficult. Spectral representation (frequency domain) is one of the most effective ways to reduce the large computational workload in CNN models, and thus beneficial for any processing platform. By reducing the size of feature maps, a compact spectral CNN model is proposed and developed in this paper by utilizing just the lower frequency components of the feature maps. When compared to similar models in the spatial domain, the proposed compact spectral CNN model achieves at least 24.11\(\times \) and 4.96\(\times \) faster classification speed on AT &T face recognition and MNIST digit/fashion classification datasets, respectively.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Almasi, A.D., Wozniak, S., Cristea, V., Leblebici, Y., Engbersen, T.: Review of advances in neural networks: neural design technology stack. Nerocomputing 174, 31ā41 (2016)
Collobert, R., Weston, J.: A unified architecture for natural language processing: deep neural networks with multitask learning. In: Proceedings of the 25th International Conference on Machine Learning, pp. 160ā167. ACM (2008)
Simard, P.Y., Steinkraus, D., Platt, J.C.: Best practices for convolutional neural networks applied to visual document analysis. In: Proceedings of the 7th International Conference on Document Analysis and Recognition (ICDAR), vol. 3, pp. 958ā963. IEEE (2003)
McNelis, P.D.: Neural Networks in Finance: Gaining Predictive Edge in the Market. Academic Press, Cambridge (2005)
Ahmad Radzi, S., Mohamad, K.H., Liew, S.S., Bakhteri, R.: Convolutional neural network for face recognition with pose and illumination variation. Int. J. Eng. Technol. (IJET) 6(1), 44ā57 (2014)
Huang, P.S., He, X., Gao, J., Deng, L., Acero, A., Heck, L.: Learning deep structured semantic models for web search using clickthrough data. In: Proceedings of the 22nd ACM International Conference on Information & Knowledge Management, pp. 2333ā2338. ACM (2013)
Rasti, P., Uiboupin, T., Escalera, S., Anbarjafari, G.: Convolutional neural network super resolution for face recognition in surveillance monitoring. In: Perales, F.J.J., Kittler, J. (eds.) AMDO 2016. LNCS, vol. 9756, pp. 175ā184. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-41778-3_18
Yeap, Y.Y., Sheikh, U.U., Ab Rahman, A.A.: Image forensic for digital image copy move forgery detection. In: 14th IEEE International Colloquium on Signal Processing and Its Applications (CSPA), pp. 239ā244. IEEE (2018)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. Commun. ACM 60(6), 84ā90 (2017)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: Proceedings of the 3rd International Conference on Learning Representations, ICLR (2015)
Sermanet, P., et al.: A multirange architecture for collision-free off-road robot navigation. J. Field Robot. 26(1), 52ā87 (2009)
LeCun, Y., et al.: Handwritten digit recognition with a back-propagation network. In: Proceedings of the 2nd International Conference on Neural Information Processing Systems (NIPS), pp. 396ā404. NeurIPS (1989)
Zhang, Q., Zhang, M., Chen, T., Sun, Z., Ma, Y., Yu, B.: Recent advances in convolutional neural network acceleration. Neurocomputing 323, 37ā51 (2019)
Amer, H., Ab Rahman, A., Amer, I., Lucarz, C., Mattavelli, M.: Methodology and technique to improve throughput of FPGA-based Cal dataflow programs: case study of the RVC MPEG-4 SP intra decoder. In: Proceedings of the IEEE Workshop on Signal Processing Systems (SiPS), pp. 186ā191. IEEE (2011)
Ayat, S., Khalil-Hani, M., Ab Rahman, A., Abdellatef, H.: Spectral-based convolutional neural network without multiple spatial-frequency domain switchings. Neurocomputing 364, 152ā167 (2019)
Rizvi, S., Ab Rahman, A., Khalil-Hani, M., Ayat, S.: A low-complexity complex-valued activation function for fast and accurate spectral domain convolutional neural network. Indones. J. Electr. Eng. Inform. (IJEEI) 9(1), 173ā184 (2021)
Liu, S., Luk, W.: Optimizing fully spectral convolutional neural networks on FPGA. In: Proceedings of the 19th IEEE International Conference on Field-Programmable Technology (ICFPT), pp. 39ā47. IEEE (2020)
Watanabe, T., Wolf, D.: Image classification in frequency domain with 2SReLU: a second harmonics superposition activation function. Appl. Soft Comput. 112, 107851 (2021)
Zhang, C., Li, P., Sun, G., Guan, Y., Xiao, B., Cong, J.: Optimizing FPGA-based accelerator design for deep convolutional neural networks. In: Proceedings of the 2015 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays, pp. 161ā170. ACM (2015)
Qiu, J., et al.: Going deeper with embedded FPGA platform for convolutional neural network. In: Proceedings of the 2016 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays, pp. 26ā35. ACM (2016)
Ristretto, G.P.: Hardware-oriented approximation of convolutional neural networks. arXiv preprint (arXiv:1605.06402). arXiv (2016)
Denton, E.L., Zaremba, W., Bruna, J., LeCun, Y., Fergus, R.: Exploiting linear structure within convolutional networks for efficient evaluation. In: Proceedings of the Advances in Neural Information Processing Systems, pp. 1269ā1277. NeurIPS (2014)
Han, S., Pool, J., Tran, J., Dally, W.: Learning both weights and connections for efficient neural network. In: Proceedings of the 28th International Conference on Neural Information Processing Systems (NIPS), pp. 1135ā1143. NeurIPS (2015)
Shawahna, A., Sait, S.M., El-Maleh, A.: FPGA-based accelerators of deep learning networks for learning and classification: a review. IEEE Access 7, 7823ā59 (2018)
Zhang, X., Zou, J., Ming, X., He, K., Sun, J.: Efficient and accurate approximations of nonlinear convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and pattern Recognition (CVPR), pp. 1984ā1992. IEEE (2015)
Courbariaux, M., Hubara, I., Soudry, D., El-Yaniv, R., Bengio, Y.: Binarized neural networks: Training deep neural networks with weights and activations constrained to +1 or -1. arXiv preprint (arXiv:1602.02830). arXiv (2016)
Hubara, I., Courbariaux, M., Soudry, D., El-Yaniv, R., Bengio, Y.: Binarized neural networks. In: Proceedings of the Advances in Neural Information Processing Systems, pp. 4107ā4115. NeurIPS (2016)
Liang, S., Yin, S., Liu, L., Luk, W., Wei, S.: FP-BNN: binarized neural network on FPGA. Neurocomputing 275, 1072ā1086 (2018)
Wu, Q., Lu, X., Xue, S., Wang, C., Wu, X., Fan, J.: SBNN: slimming binarized neural network. Neurocomputing 401, 113ā122 (2020)
Mittal, S.: A survey of FPGA-based accelerators for convolutional neural networks. Neural Comput. Appl. 32(4), 1109ā1139 (2018). https://doi.org/10.1007/s00521-018-3761-1
Umuroglu, Y., et al.: A framework for fast, scalable binarized neural network inference. In: Proceedings of the 2017 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays, pp. 65ā74. ACM (2017)
Ma, X., et al.: An area and energy efficient design of domain-wall memory-based deep convolutional neural networks using stochastic computing. In: Proceedings of the 19th International Symposium on Quality Electronic Design (ISQED), pp. 314ā321. IEEE (2018)
Li, J., et al.: Hardware-driven nonlinear activation for stochastic computing based deep convolutional neural networks. In: Proceedings of the International Joint Conference on Neural Networks (IJCNN), pp. 1230ā1236. IEEE (2017)
Li, Z., et al.: HEIF: highly efficient stochastic computing-based inference framework for deep neural networks. IEEE Trans. Comput.-Aid. Des. Integr. Circ. Syst. 38(8), pp. 1543ā1556 (2019)
Abdellatef, H., Khalil-Hani, M., Shaikh-Husin, N., Ayat, S.: Accurate and compact convolutional neural network based on stochastic computing. Neurocomputing 471, 31ā47 (2022)
Qian, W., Li, X., Riedel, M.D., Bazargan, K., Lilja, D.J.: An architecture for fault-tolerant computation with stochastic logic. IEEE Trans. Comput. 60(1), 93ā105 (2010)
Hayes, J.P.: Introduction to stochastic computing and its challenges. In: Proceedings of the 52nd ACM/IEEE Design Automation Conference (DAC), pp. 1ā3. IEEE (2015)
Bottleson, J., Kim, S., Andrews, J., Bindu, P., Murthy, D.N., Jin, J.: clCaffe: OpenCL accelerated Caffe for convolutional neural networks. In: Proceedings of the IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW), pp. 50ā57. IEEE (2016)
Bareiss, E.H.: Numerical solution of linear equations with Toeplitz and vector Toeplitz matrices. Numerische Mathematik 13(5), 404ā424 (1969)
Sze, V., Chen, Y.H., Yang, T.J., Emer, J.S.: Efficient processing of deep neural networks: a tutorial and survey. Proc. IEEE 105(12), 2295ā2329 (2017)
Winograd, S.: Arithmetic Complexity of Computations. SIAM (1980)
Lavin, A., Gray, S.: Fast algorithms for convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4013ā4021. IEEE (2016)
Rippel, O., Snoek, J., Adams, R.P.: Spectral representations for convolutional neural networks. In: Proceedings of the 28th International Conference on Neural Information Processing Systems (NIPS), pp. 2449ā2457. ACM (2015)
Ayat, S., Khalil-Hani, M., Ab Rahman, A.: Optimizing FPGA-based CNN accelerator for energy efficiency with an extended Roofline model. Turk. J. Electr. Eng. Comput. Sci. 26(2), 919ā935 (2018)
Niu, Y., et al.: SPEC2: SPECtral SParsE CNN accelerator on FPGAs. In: Proceedings of the 26th IEEE International Conference on High Performance Computing, Data, and Analytics (HiPC), pp. 195ā204. IEEE (2019)
Sun, W., Zeng, H., Yang, Y.-h., Prasanna, V.: Throughput-optimized frequency domain CNN with fixed-point quantization on FPGA. In: International Conference on ReConFigurable Computing and FPGAs (ReConFig), pp. 1ā8. IEEE (2018)
Guan, B., Zhang, J., Sethares, W., Kijowski, R., Liu, F.: Spectral domain convolutional neural network. In: Proceedings of the 46th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2795ā2799. IEEE (2021)
LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436ā444 (2015)
Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv preprint (arXiv:1502.03167). arXiv (2015)
Vedaldi, A., Lenc, K.: MatConvNet: convolutional neural networks for MATLAB. In: Proceedings of the 23rd ACM International Conference on Multimedia (MM), pp. 689ā692. ACM (2015)
Cong, J., Xiao, B.: Minimizing computation in convolutional neural networks. In: Proceedings of the 24th International Conference on Artificial Neural Networks (ICANN), pp. 281ā290. IEEE (2014)
Acknowledgment
The authors thank Universiti Teknologi Malaysia (UTM) for their support under the Research University Grant (GUP), grant number 16J83.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
Ā© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Ayat, S.O., Rizvi, S.M., Abdellatef, H., Ab Rahman, A.AH., Manan, S.S.A. (2023). A Compact Spectral Model forĀ Convolutional Neural Network. In: Arai, K. (eds) Proceedings of the Future Technologies Conference (FTC) 2022, Volume 1. FTC 2022 2022. Lecture Notes in Networks and Systems, vol 559. Springer, Cham. https://doi.org/10.1007/978-3-031-18461-1_7
Download citation
DOI: https://doi.org/10.1007/978-3-031-18461-1_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-18460-4
Online ISBN: 978-3-031-18461-1
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)