Journal of the Korea Institute of Information and Communication Engineering (한국정보통신학회논문지)

The Korea Institute of Information and Commucation Engineering (한국정보통신학회)
권호 표지
DOI QR코드

DOI QR Code

Convolutional Neural Network Based on Accelerator-Aware Pruning for Object Detection in Single-Shot Multibox Detector

싱글숏 멀티박스 검출기에서 객체 검출을 위한 가속 회로 인지형 가지치기 기반 합성곱 신경망 기법

  • Kang, Hyeong-Ju (School of Computer Science and Engineering, Korea University of Technology and Education)
  • Received : 2019.11.20
  • Accepted : 2019.12.28
  • Published : 2020.01.31
Download PDF
⟨ Previous Next ⟩

Abstract

Convolutional neural networks (CNNs) show high performance in computer vision tasks including object detection, but a lot of weight storage and computation is required. In this paper, a pruning scheme is applied to CNNs for object detection, which can remove much amount of weights with a negligible performance degradation. Contrary to the previous ones, the pruning scheme applied in this paper considers the base accelerator architecture. With the consideration, the pruned CNNs can be efficiently performed on an ASIC or FPGA accelerator. Even with the constrained pruning, the resulting CNN shows a negligible degradation of detection performance, less-than-1% point degradation of mAP on VOD0712 test set. With the proposed scheme, CNNs can be applied to objection dtection efficiently.

Keywords

References

  1. K. Simonyan, and A. Zisserman, "Very deep convolutional networks for large-scale image recognition," in Proceedings of International Conference on Learning Representations, pp. 1-14, 2015.
  2. W. Liu, D. Anguelov, D. Erhan, C. Szegedy, S. Reed, C.-Y. Fu, and A. C. Berg, "SSD: Single shot multibox detector," in Proceedings of European Conference on Computer Vision, pp. 21-37, 2016.
  3. S. Han, J. Pool, J. Tran, and W. J. Dally, "Learning both weights and connections for efficient neural networks," in Proceedings of Advances in Neural Information Processing Systems, pp. 1135-1143, 2015.
  4. W. Wen, C. Wu, Y. Wang, Y. Chen, and H. Li, "Learning structured sparsity in deep neural networks," in Proceedings of Advances in Neural Information Processing Systems, pp. 2074-2082, 2016.
  5. Y. He, X. Zhang, and J. Sun, "Channel pruning for accelerating very deep neural networks," in Proceedings of International Conference on Computer Vision, pp. 1398-1406, 2017.
  6. V. Lebedev, and V. Lempitsky, "Fast ConvNets using group-wise brain damage," in Proceedings of Computer Vision and Pattern Recognition, pp. 2554-2564, 2016.
  7. J. Yu, A. Lukefahr, D. Palframan, G. Dasika, R. Das, and S. Mahlke, "Scalpel: Customizing DNN pruning to the underlying hardware parallelism," in Proceedings of International Symposium on Computer Architecture, pp. 548-560, 2017.
  8. H.-J. Kang, "Accelerator-aware pruning for convolutional neural networks," IEEE Transactions on Circuits and Systems for Video Technology, in press.
  9. Y. Ma, T. Zheng, Y. Cao, S. Vrudhula, and J. Seo, "Algorithm-Hardware co-design of single shot detector for fast object detection on FPGAs," in Proceedings of International Conference on Computer-Aided Design, pp. 1-8, 2018.