Journal of IKEEE (전기전자학회논문지)

Institute of Korean Electrical and Electronics Engineers (한국전기전자학회)
권호 표지
DOI QR코드

DOI QR Code

Efficient Convolutional Neural Network with low Complexity

저연산량의 효율적인 콘볼루션 신경망

  • Lee, Chanho (Dept. of Information and telecommunications Engineering, Soongsil University) ;
  • Lee, Joongkyung (Dept. of Information and telecommunications Engineering, Soongsil University) ;
  • Ho, Cong Ahn (Dept. of Information and telecommunications Engineering, Soongsil University)
  • Received : 2020.05.31
  • Accepted : 2020.08.18
  • Published : 2020.09.30
Download PDF
⟨ Previous Next ⟩

Abstract

We propose an efficient convolutional neural network with much lower computational complexity and higher accuracy based on MobileNet V2 for mobile or edge devices. The proposed network consists of bottleneck layers with larger expansion factors and adjusted number of channels, and excludes a few layers, and therefore, the computational complexity is reduced by half. The performance the proposed network is verified by measuring the accuracy and execution times by CPU and GPU using ImageNet100 dataset. In addition, the execution time on GPU depends on the CNN architecture.

휴대용 기기나 에지 단말을 위한 CNN인 MobileNet V2를 기반으로 연산량을 크게 줄이면서도 정확도는 증가시킨 효율적인 인공신경망 네트워크 구조를 제안한다. 제안하는 구조는 Bottleneck 층 구조를 유지하면서 확장 계수를 증가시키고 일부 층을 제거하는 등의 변화를 통해 연산량을 절반 이하로 줄였다. 설계한 네트워크는 ImageNet100 데이터셋을 이용하여 분류 정확도와 CPU 및 GPU에서의 연산 시간을 측정하여 그 성능을 검증 하였다. 또한, 현재 딥러닝 가속기로 널리 이용하는 GPU에서 네트워크 구조에 따라 동작 성능이 달라짐도 보였다.

Keywords

References

  1. K. Simonyan, A. Zisserman, "Very Deep Convolutional Network for Large-scale image Recognition," 2015 International Conference on Learning Representations (ICLR), San Diego, USA, pp.7-9, 2015.
  2. C. Szegedy, X. Zhang, S. Ren, J. Sun, "Going Deeper with Convolutions," 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, Massachusetts, USA, pp.1-9, 2015. DOI: 10.1109/CVPR.2015.7298594
  3. K. He, "Deep residual Learning for Image Recognition," 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, Nevada, pp.770-778, 2016. DOI: 10.1109/CVPR.2016.90
  4. François Chollet, "Xception: Deep Learning with Depthwise Separable Convolutions," 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.1801-1807, 2016.
  5. "Densely Connected Convolutional Networks," 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.2261-2269, 2016. DOI: 10.1109/CVPR.2017.243
  6. J. Hu, L. Shen and G. Sun, "Squeeze-and-Excitation Networks," 2018 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.7132-7141, 2018. DOI: 10.1109/CVPR.2018.00745
  7. A. 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: 1704.04861, 2017
  8. N. Ma, X. Zhang, H. T. Zheng, J. Sun, "ShuffleNet v2: Pratical Guidelines for Efficient CNN Architectur Design," The 16th European Conference on Computer Vision (ECCV), 8-14, pp.116-131, 2018.
  9. M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, L. C. Chen, "Mobilenet v2: Inverted residuals and Linear Bottlenecks," 2018 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 18-22, pp.4510-4520, 2018. DOI: 10.1109/CVPR.2018.00474