Accelerating Very Deep Convolutional Networks for Classification and Detection

  title={Accelerating Very Deep Convolutional Networks for Classification and Detection},
  author={Xiangyu Zhang and Jianhua Zou and Kaiming He and Jian Sun},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
This paper aims to accelerate the test-time computation of convolutional neural networks (CNNs), especially very deep CNNs <xref ref-type="bibr" rid="ref1">[1]</xref> that have substantially impacted the computer vision community. Unlike previous methods that are designed for approximating linear filters or linear responses, our method takes the nonlinear units into account. We develop an effective solution to the resulting nonlinear optimization problem without the need of stochastic gradient… CONTINUE READING
Highly Influential
This paper has highly influenced 18 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 169 citations. REVIEW CITATIONS
Recent Discussions
This paper has been referenced on Twitter 5 times over the past 90 days. VIEW TWEETS
105 Citations
66 References
Similar Papers


Publications citing this paper.
Showing 1-10 of 105 extracted citations

170 Citations

Citations per Year
Semantic Scholar estimates that this publication has 170 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-10 of 66 references

and G

  • A. Krizhevsky, I. Sutskever
  • Hinton, “Imagenet classifi- 800 cation with deep…
  • 2012
Highly Influential
10 Excerpts

806 and Y

  • P. Sermanet, D. Eigen, X. Zhang, M. Mathieu, R. Fergus
  • LeCun, “Overfeat: Integrated recognition…
  • 2014
Highly Influential
5 Excerpts

851 S

  • O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh
  • Ma, Z. Huang, A. Karpathy, A. Khosla, M…
  • 2014
Highly Influential
4 Excerpts

and M

  • V. Vanhoucke, A. Senior
  • Z. Mao, “Improving the 837 speed of neural…
  • 2011
Highly Influential
7 Excerpts

and T

  • J. Long, E. Shelhamer
  • Darrell, “Fully convolutional 827 networks for…
  • 2015
Highly Influential
5 Excerpts

and V

  • V. Lebedev, Y. Ganin, M. Rakhuba, I. Oseledets
  • Lem- 847 pitsky, “Speeding-up convolutional…
  • 2015
Highly Influential
7 Excerpts

Procrustes problems

  • J. C. Gower, G. B. Dijksterhuis
  • Oxford 879 University Press Oxford
  • 2004
Highly Influential
9 Excerpts

813 D

  • C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov
  • Erhan, V. Vanhoucke, and A. Rabinovich, “Going…
  • 2015
1 Excerpt

Similar Papers

Loading similar papers…