Papers › PerforatedCNNs: Acceleration through Elimination of Redundant Convolutions

PerforatedCNNs: Acceleration through Elimination of Redundant Convolutions

30 Apr 2015NeurIPS 2016 12arXiv:1504.08362archive 2025-07-28

Michael Figurnov, Aijan Ibraimova, Dmitry Vetrov, Pushmeet Kohli

We propose a novel approach to reduce the computational cost of evaluation of convolutional neural networks, a factor that has hindered their deployment in low-power devices such as mobile phones. Inspired by the loop perforation technique from source code optimization, we speed up the bottleneck convolutional layers by skipping their evaluation in some of the spatial positions. We propose and analyze several strategies of choosing these positions. We demonstrate that perforation can accelerate modern convolutional networks such as AlexNet and VGG-16 by a factor of 2x - 4x. Additionally, we show that perforation is complementary to the recently proposed acceleration method of Zhang et al.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

mfigurnov/perforated-cnn-caffe officialmentioned in papermentioned on GitHubNOASSERTION report
mfigurnov/perforated-cnn-matconvnet officialmentioned in papermentioned on GitHubNOASSERTION report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

1x1 ConvolutionConvolutionDense ConnectionsDropoutGrouped ConvolutionLocal Response NormalizationMax PoolingReLUSPEEDSoftmax

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections