Faster CNNs with Direct Sparse Convolutions and Guided Pruning

  title={Faster CNNs with Direct Sparse Convolutions and Guided Pruning},
  author={JongSoo Park and Sheng R. Li and Wei Wen and Ping Tak Peter Tang and Hai Li and Yiran Chen and Pradeep Dubey},
Phenomenally successful in practical inference problems, convolutional neural networks (CNN) are widely deployed in mobile devices, data centers, and even supercomputers. The number of parameters needed in CNNs, however, are often large and undesirable. Consequently, various methods have been developed to prune a CNN once it is trained. Nevertheless, the resulting CNNs offer limited benefits. While pruning the fully connected layers reduces a CNN’s size considerably, it does not improve… CONTINUE READING
Highly Cited
This paper has 37 citations. REVIEW CITATIONS


Publications citing this paper.


Publications referenced by this paper.
Showing 1-10 of 36 references

Fast Algorithms for Convolutional Neural Networks

  • Andrew Lavin, Scott Gray
  • arXiv preprint arXiv:1509.09308,
  • 2015
Highly Influential
4 Excerpts

Similar Papers

Loading similar papers…