publication . Preprint . 2015

PerforatedCNNs: Acceleration through Elimination of Redundant Convolutions

Figurnov, Michael; Ibraimova, Aijan; Vetrov, Dmitry; Kohli, Pushmeet;
Open Access English
  • Published: 30 Apr 2015
Abstract
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 accelera...
Subjects
free text keywords: Computer Science - Computer Vision and Pattern Recognition
Download from
35 references, page 1 of 3

Ba, Jimmy, Salakhutdinov, Ruslan R, Grosse, Roger B, and Frey, Brendan J. Learning wake-sleep recurrent attention models. In Advances in Neural Information Processing Systems, pp. 2575-2583, 2015.

Chen, Tianqi. Matrix shadow library. https://github.com/dmlc/mshadow, 2015.

Chetlur, Sharan, Woolley, Cliff, Vandermersch, Philippe, Cohen, Jonathan, Tran, John, Catanzaro, Bryan, and Shelhamer, Evan. cuDNN: Efficient primitives for deep learning. arXiv preprint arXiv:1410.0759, 2014. [OpenAIRE]

Collins, Maxwell D. and Kohli, Pushmeet. Memory bounded deep convolutional networks. arXiv preprint arXiv:1412.1442, 2014. [OpenAIRE]

Courbariaux, Matthieu, Bengio, Yoshua, and David, Jean-Pierre. Low precision arithmetic for deep learning. ICLR, 2015.

Denton, Emily L, Zaremba, Wojciech, Bruna, Joan, LeCun, Yann, and Fergus, Rob. Exploiting linear structure within convolutional networks for efficient evaluation. NIPS 27, pp. 1269-1277, 2014.

Graham, Benjamin. Fractional max-pooling. arXiv preprint arXiv:1412.6071, 2014a.

Graham, Benjamin. Spatially-sparse convolutional neural networks. arXiv preprint arXiv:1409.6070, 2014b.

Gupta, Suyog, Agrawal, Ankur, Gopalakrishnan, Kailash, and Narayanan, Pritish. Deep learning with limited numerical precision. ICML, 2015. [OpenAIRE]

He, Kaiming and Sun, Jian. Convolutional neural networks at constrained time cost. CVPR, 2015.

Jaderberg, Max, Vedaldi, Andrea, and Zisserman, Andrew. Speeding up convolutional neural networks with low rank expansions. BMVC, 2014. [OpenAIRE]

Jaderberg, Max, Simonyan, Karen, Zisserman, Andrew, et al. Spatial transformer networks. In Advances in Neural Information Processing Systems, pp. 2008-2016, 2015. [OpenAIRE]

Jia, Yangqing, Shelhamer, Evan, Donahue, Jeff, Karayev, Sergey, Long, Jonathan, Girshick, Ross, Guadarrama, Sergio, and Darrell, Trevor. Caffe: Convolutional architecture for fast feature embedding. In Proceedings of the ACM International Conference on Multimedia, pp. 675-678. ACM, 2014.

Jin, Jonghoon, Dundar, Aysegul, and Culurciello, Eugenio. Flattened convolutional neural networks for feedforward acceleration. ICLR, 2015.

Krizhevsky, Alex, Sutskever, Ilya, and Hinton, Geoffrey E. Imagenet classification with deep convolutional neural networks. NIPS 25, pp. 1097-1105, 2012.

35 references, page 1 of 3
Abstract
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 accelera...
Subjects
free text keywords: Computer Science - Computer Vision and Pattern Recognition
Download from
35 references, page 1 of 3

Ba, Jimmy, Salakhutdinov, Ruslan R, Grosse, Roger B, and Frey, Brendan J. Learning wake-sleep recurrent attention models. In Advances in Neural Information Processing Systems, pp. 2575-2583, 2015.

Chen, Tianqi. Matrix shadow library. https://github.com/dmlc/mshadow, 2015.

Chetlur, Sharan, Woolley, Cliff, Vandermersch, Philippe, Cohen, Jonathan, Tran, John, Catanzaro, Bryan, and Shelhamer, Evan. cuDNN: Efficient primitives for deep learning. arXiv preprint arXiv:1410.0759, 2014. [OpenAIRE]

Collins, Maxwell D. and Kohli, Pushmeet. Memory bounded deep convolutional networks. arXiv preprint arXiv:1412.1442, 2014. [OpenAIRE]

Courbariaux, Matthieu, Bengio, Yoshua, and David, Jean-Pierre. Low precision arithmetic for deep learning. ICLR, 2015.

Denton, Emily L, Zaremba, Wojciech, Bruna, Joan, LeCun, Yann, and Fergus, Rob. Exploiting linear structure within convolutional networks for efficient evaluation. NIPS 27, pp. 1269-1277, 2014.

Graham, Benjamin. Fractional max-pooling. arXiv preprint arXiv:1412.6071, 2014a.

Graham, Benjamin. Spatially-sparse convolutional neural networks. arXiv preprint arXiv:1409.6070, 2014b.

Gupta, Suyog, Agrawal, Ankur, Gopalakrishnan, Kailash, and Narayanan, Pritish. Deep learning with limited numerical precision. ICML, 2015. [OpenAIRE]

He, Kaiming and Sun, Jian. Convolutional neural networks at constrained time cost. CVPR, 2015.

Jaderberg, Max, Vedaldi, Andrea, and Zisserman, Andrew. Speeding up convolutional neural networks with low rank expansions. BMVC, 2014. [OpenAIRE]

Jaderberg, Max, Simonyan, Karen, Zisserman, Andrew, et al. Spatial transformer networks. In Advances in Neural Information Processing Systems, pp. 2008-2016, 2015. [OpenAIRE]

Jia, Yangqing, Shelhamer, Evan, Donahue, Jeff, Karayev, Sergey, Long, Jonathan, Girshick, Ross, Guadarrama, Sergio, and Darrell, Trevor. Caffe: Convolutional architecture for fast feature embedding. In Proceedings of the ACM International Conference on Multimedia, pp. 675-678. ACM, 2014.

Jin, Jonghoon, Dundar, Aysegul, and Culurciello, Eugenio. Flattened convolutional neural networks for feedforward acceleration. ICLR, 2015.

Krizhevsky, Alex, Sutskever, Ilya, and Hinton, Geoffrey E. Imagenet classification with deep convolutional neural networks. NIPS 25, pp. 1097-1105, 2012.

35 references, page 1 of 3
Powered by OpenAIRE Research Graph
Any information missing or wrong?Report an Issue