Browse > Article
http://dx.doi.org/10.9717/kmms.2021.24.11.1552

A Study on the Optimization of Convolution Operation Speed through FFT Algorithm  

Lim, Su-Chang (Dept. of Computer Engineering, Sunchon National University)
Kim, Jong-Chan (Dept. of Computer Engineering, Sunchon National University)
Publication Information
Journal of Korea Multimedia Society / v.24, no.11, 2021 , pp. 1552-1559 More about this Journal
Abstract
Convolution neural networks (CNNs) show notable performance in image processing and are used as representative core models. CNNs extract and learn features from large amounts of train dataset. In general, it has a structure in which a convolution layer and a fully connected layer are stacked. The core of CNN is the convolution layer. The size of the kernel used for feature extraction and the number that affect the depth of the feature map determine the amount of weight parameters of the CNN that can be learned. These parameters are the main causes of increasing the computational complexity and memory usage of the entire neural network. The most computationally expensive components in CNNs are fully connected and spatial convolution computations. In this paper, we propose a Fourier Convolution Neural Network that performs the operation of the convolution layer in the Fourier domain. We work on modifying and improving the amount of computation by applying the fast fourier transform method. Using the MNIST dataset, the performance was similar to that of the general CNN in terms of accuracy. In terms of operation speed, 7.2% faster operation speed was achieved. An average of 19% faster speed was achieved in experiments using 1024x1024 images and various sizes of kernels.
Keywords
Computer Vision; Convolution Neural Networks; Deep Learning; Fast Fourier Transform; Convolution;
Citations & Related Records
연도 인용수 순위
  • Reference
1 Convolutional Neural Networks (CNN): Step 1-Convolution Operation. https://www.superdatascience.com/blogs/convolutional-neuralnetworks-cnn-step-1-convolution-operation (accessed November 06, 2021).
2 S. Srinivas and R.V. Babu, "Learning Neural Network Architectures using Backpropagation," arXiv preprint, arXiv:1511.05497, 2015.
3 S.W. Park, S.H. Kim, S.C. Lim, and D.Y. Kim, "Performance Comparison of Commercial and Customized CNN for Detection in Nodular Lung Cancer," Journal of Korea Multimedia Society, Vol. 23, No. 6, pp. 729-737, 2020.
4 S.C. Lim and D.Y. Kim, "Semantic Segmentation using Convolutional Neural Network with Conditional Random Field," The Journal of the Korea Institute of Electronic Communication Sciences, Vol. 12, No. 3, pp. 451-456, 2017.   DOI
5 S.C. Lim, S.W. Park, J.C. Kim, and C.S. Ryu, "Object Tracking Algorithm using Feature Map based on Siamese Network," Journal of Korea Multimedia Society, Vol. 24, No. 6, pp. 796-804, 2020.   DOI
6 C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich, "Going Deeper with Convolutions," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1-9, 2015.
7 Y. LeCun, B. Boser, J.S. DDenker, D. Henderson, R.E. Howard, W. Hubbard, and L.D. Jackel, "Backpropagation Applied to Handwritten Zip Code Recognition," Neural Computation, Vol. 1, No. 4, pp. 541-551, 1989.   DOI
8 O. Russakovsky, et al, "Imagenet Large Scale Visual Recognition Challenge," International Journal of Computer Vision, Vol. 115, No. 3 pp. 211-252, 2015.   DOI
9 A. Krizhevsky, I. Sutskever, and G.E. Hinton, "Imagenet Classification with Deep Convolutional Neural Networks," Proceeding of International Conference on Advances in Neural Information Processing Systems, pp. 1097-1105, 2012.
10 P. Sermanet, D. Eigen, X. Zhang, M. Mathieu, R. Fergus, and Y. LeCun, "Overfeat: Integrated Recognition, Localization and Detection Using Convolutional Networks," arXiv preprint, arXiv:1312.6229, 2013.
11 S.C. Lim and D.Y. Kim, "Apply Locally Weight Parameter Elimination for CNN Model Compression," The Korea Institute of Information and Commucation Engineering, Vol. 22, No. 9, pp. 1165-1171, 2018.
12 X. Zhang, X. Zhou, M. Lin, and J. Sun, "Shuffle Net: An Exteremey Efficient Convolutional Neural Network for Mobile Devices," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6848-6856, 2018.
13 Y. Gong, L. Liu, M. Yang, and L. Bourdev, "Compressing Deep Convolutional Networks Using Vector Quantization," arXiv preprint, arXiv:1412.6115, 2014.
14 A.G. Howard, M. Zhu, B. Chen, D. Kalenichenko, W. Wang, T. Weyand, M. Andreetto, and H. Adam, "MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications," arXiv preprint, arXiv:1704.04861, 2017.
15 M. Denil, B. Shakini, L. Dinh, M.A. Ranzato, and N.D. Freitas, "Predicting Parameters in Deep Learning," Proceedings of the 26th International Conference on Neural Information Processing Systems, Vol. 2, pp. 2148-2156, 2013.
16 E.L. Denton, W. Zaremba, J. Bruna, Y. LeCun, and R. Fergus, "Exploiting Linear Structure within Convolutional Networks for Efficient Evaluation," Advances in Neural Information Processing Systems, pp. 1269-1277, 2014.
17 V. Vanhoucke, A. Senior, and M.Z Mao, "Improving the Speed of Neural Networks on Cpus," Proceedings of Deep Learning and Unsupervised Feature Learning NIPS Workshop, Vol. 1. pp. 1-8, 2011.
18 W. Chen, J.T. Wilson, S. Tyree, K.Q. Weinberger, and Y. Chen, "Compressing Neural Networks with the Hashing Trick," Proceedings of International Conference on Machine Learning, pp. 2285-2294, 2015.
19 K. He, X. Zhang, S. Ren, and J. Sun, "Deep Residual Learning for Image Recognition," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770-778, 2016.