Advertisement

Journal of Signal Processing Systems

, Volume 90, Issue 6, pp 877–890 | Cite as

Efficient Object Detection Using Embedded Binarized Neural Networks

  • Jaeha Kung
  • David Zhang
  • Gooitzen van der Wal
  • Sek Chai
  • Saibal Mukhopadhyay
Article

Abstract

Memory performance is a key bottleneck for deep learning systems. Binarization of both activations and weights is one promising approach that can best scale to realize the highest energy efficient system using the lowest possible precision. In this paper, we utilize and analyze the binarized neural network in doing human detection on infrared images. Our results show comparable algorithmic performance of binarized versus 32bit floating-point networks, with the added benefit of greatly simplified computation and reduced memory overhead. In addition, we present a system architecture designed specifically for computation using binary representation that achieves at least 4× speedup and the energy is improved by three orders of magnitude over GPU.

Keywords

Deep learning Embedded computer vision Binary neural network Low-power object detection 

Notes

Acknowledgments

This research was developed with funding from the Defense Advanced Research Projects Agency (DARPA), the Air Force Research Laboratory (AFRL), and NSF (#1526399). The views, opinions and/or findings expressed are those of the authors and should not be interpreted as representing the official views or policies of the Department of Defense or the U.S. Government.

References

  1. 1.
    Krizhevsky, A. et. al. (2012). ImageNet classification with deep convolutional neural networks. In: Proc Neural Information Processing Systems (NIPS), pp. 1097–1105.Google Scholar
  2. 2.
    Sermanet, P., Kavukcuoglu, K., Chintala, S., & Lecun, Y. (2013). Pedestrian detection with unsupervised multi-stage feature learning. In Proc Comput Vision Pattern Recog (CVPR), pp. 3626–3633, IEEE.Google Scholar
  3. 3.
    Sutskever, I., Martens, J., & Hinton, G. (2011). Generating text with recurrent neural networks. In Proc Int Conf Machine Learning (ICML), pp. 1017–1024.Google Scholar
  4. 4.
    Collobert, R., et al. (2011). Natural language processing (almost) from scratch. J. Machine Learning Research, 12, 2493–2537.MATHGoogle Scholar
  5. 5.
    LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521, 436–444.CrossRefGoogle Scholar
  6. 6.
    Vanhoucke, V., & Senior, A. (2011). Improving the speed of neural networks on CPUs. In Proc Deep Learn Unsupervised Feature Learn. NIPS: Workshop.Google Scholar
  7. 7.
    Kung, J., Kim, D. & Mukhopadhyay, S. (2015). A power-aware digital feedforward neural network platform with backpropagation driven approximate synapses. In Int Symp Low Power Electron, Design (ISLPED), pp. 85–90.Google Scholar
  8. 8.
    Sarwar, S. S., Venkataramani, S., Raghunathan, A., & Roy, K. (2016). Multiplier-less artificial neurons exploiting error resiliency for energy-efficient neural computing. In Proc Design Automat, Test in Europe (DATE), pp. 145–150.Google Scholar
  9. 9.
    Gong, Y., Liu, L., Yang, M. & Bourdev, L. (2014). Compressing deep convolutional networks using vector quantization. arXiv preprint arXiv:1412.6115.Google Scholar
  10. 10.
    Han, S. et al. (2016). EIE: Efficient inference engine on compresses deep neural network. arXiv preprint arXiv:1602:01528.Google Scholar
  11. 11.
    Courbariaux, M. et al. (2016). Binarized neural networks: Training neural networks with weights and activations constrained to +1 or −1. arXiv preprint arXiv:1602.02830.Google Scholar
  12. 12.
    Rastegari, M., Ordonez, V., Redmon, J., & Farhadi, A. (2016). XNOR-net: ImageNet classification using binary convolutional neural networks. arXiv preprint arXiv:1603.05279.Google Scholar
  13. 13.
    Zhou, S. et al. (2016). DoReFa-net: Training low bitwidth convolutional neural networks with low bitwidth gradients. arXiv preprint arXiv:1606.06160.Google Scholar
  14. 14.
    LeCun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998). Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11), 2278–2324.CrossRefGoogle Scholar
  15. 15.
    Taigman, Y., Yang, M., Ranzato, M., & Wolf, L. (2014). DeepFace: Closing the gap to human-level performance in face verification. In Proc Comput Vision Pattern Recog (CVPR), pp. 1701–1708, IEEE.Google Scholar
  16. 16.
    Coates, A. et al. (2013). Deep learning with COTS HPC systems. In Proc. Int. Conf. Machine Learning (ICML), pp. 1337–1345.Google Scholar
  17. 17.
    He, K., Zhang, X., Ren, S. & Sun, J. Deep residual learning for image recognition. arXiv preprint arXiv:1512.03385.Google Scholar
  18. 18.
    Srivastava, N., et al. (2014). Dropout: A simple way to prevent neural networks from overfitting. J. Machine Learn. Research, 15, 1928–1958.MathSciNetMATHGoogle Scholar
  19. 19.
    Wan, L. et al. (2013). Regularization of neural networks using DropConnect. In Proc Int Conf Machine Learning (ICML), pp. 1058–1066.Google Scholar
  20. 20.
    Chai, S., et al. (2016). Low precision neural network using subband decomposition. In Cognitive Architecture (CogArch). Google Scholar
  21. 21.
    Sukhbaatar, S., Bruna, J., Paluri, M., Bourdev, L., Fergus R. (2014). Training convolutional networks with noisy labels. arXiv:1406.2080.Google Scholar
  22. 22.
    Wu, Z., Fuller, N., Theriault, D., & Betke, M. (2014). A thermal infrared video benchmark for visual analysis. In Proc IEEE Workshop on Perception Beyond the Visible Spectrum (PBVS).Google Scholar
  23. 23.
    Zhang, D. et al. (2016). Unsupervised underwater fish detection fusing flow and objectiveness. In Proc Winter Appl Comput Vision Workshops (WACVW), pp. 1–7.Google Scholar
  24. 24.
    van de Sande, K. E. A., Uijlings, J. R. R., Gevers, T., & Smeulders, A. W. M. (2011). Segmentation as selective search for object recognition. In Proc Int Conf Comput Vision (ICCV).Google Scholar
  25. 25.
    Horowitz, M. Energy table for 45nm process. Stanford VLSI wiki. https://sites.google.com/site/seecproject/energy-table.
  26. 26.
    Synopsys 32/28nm generic library. https://www.synopsys.com/.

Copyright information

© Springer Science+Business Media New York 2017

Authors and Affiliations

  • Jaeha Kung
    • 1
  • David Zhang
    • 2
  • Gooitzen van der Wal
    • 2
  • Sek Chai
    • 2
  • Saibal Mukhopadhyay
    • 1
  1. 1.Georgia Institute of TechnologyAtlantaUSA
  2. 2.SRI InternationalPrincetonUSA

Personalised recommendations