The DOI matches its Crossref record; 31 of the 31 references it cites were found in a registry or an index.
Structured Pruning of Deep Convolutional Neural Networks
Abstract
Real-time application of deep learning algorithms is often hindered by high computational complexity and frequent memory accesses. Network pruning is a promising technique to solve this problem. However, pruning usually results in irregular network connections that not only demand extra representation efforts but also do not fit well on parallel computation. We introduce structured sparsity at various scales for convolutional neural networks: feature map-wise, kernel-wise, and intra-kernel strided sparsity. This structured sparsity is very advantageous for direct computational resource savings on embedded computers, in parallel computing environments, and in hardware-based systems. To decide the importance of network connections and paths, the proposed method uses a particle filtering approach. The importance weight of each particle is assigned by assessing the misclassification rate with a corresponding connectivity pattern. The pruned network is retrained to compensate for the losses due to pruning. While implementing convolutions as matrix products, we particularly show that intra-kernel strided sparsity with a simple constraint can significantly reduce the size of the kernel and feature map tensors. The proposed work shows that when pruning granularities are applied in combination, we can prune the CIFAR-10 network by more than 70% with less than a 1% loss in accuracy.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805
(2014) · Cited by 33,419
Learning Multiple Layers of Features from Tiny Images
Krizhevsky, A. (2024) · doi:10.57702/zp44cu3g · Cited by 23,395
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S. (2024) · arXiv (Cornell University) · doi:10.57702/o9raffed · Cited by 14,214
A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking
Arulampalam, M. S., Maskell, S., Gordon, N., & Clapp, T. (2002) · IEEE Transactions on Signal Processing · doi:10.1109/78.978374 · Cited by 11,502
Hinton, G., Deng, L., Yu, D., Dahl, G., Mohamed, A.-R., Jaitly, N., Senior, A., Vanhoucke, V., Nguyen, P., Sainath, T., et al. (2012) · IEEE Signal Processing Magazine · doi:10.1109/msp.2012.2205597 · Cited by 10,260
Novel approach to nonlinear/non-Gaussian Bayesian state estimation
Gordon, N. J., Salmond, D. J., & Smith, A. F. M. (1993) · IEE Proceedings F Radar and Signal Processing · doi:10.1049/ip-f-2.1993.0015 · Cited by 7,550
Reading digits in natural images with unsupervised feature learning
Netzer, Y. (2024) · doi:10.57702/e7wwo0zk · Cited by 4,149
BinaryConnect: Training Deep Neural Networks with binary weights during propagations
Courbariaux, M., Bengio, Y., & David, J.-P. (2015) · arXiv · doi:10.48550/arxiv.1511.00363 · Cited by 2,180
(2013) · Cited by 2,056
Reed, R. (1993) · IEEE Transactions on Neural Networks · doi:10.1109/72.248452 · Cited by 1,708
Proceedings of the 29th International Conference on Machine Learning (ICML-12)
Langford, J. C., & Pineau, J. (2012) · arXiv (Cornell University) · doi:10.48550/arxiv.1207.4676 · Cited by 1,618
An adaptive color-based particle filter
Nummiaro, K., Koller-Meier, E., & Van Gool, L. (2003) · Image and Vision Computing · doi:10.1016/s0262-8856(02)00129-4 · Cited by 1,157
Improved particle filter for nonlinearproblems
Carpenter, J., Clifford, P., & Fearnhead, P. (1999) · IEE Proceedings - Radar, Sonar and Navigation · doi:10.1049/ip-rsn:19990255 · Cited by 996
cuDNN: Efficient Primitives for Deep Learning
Chetlur, S., Woolley, C., Vandermersch, P., Cohen, J., Tran, J. J., Catanzaro, B., & Shelhamer, E. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1410.0759 · Cited by 943
(2006) · Cited by 490
Maintaining multimodality through mixture tracking
Vermaak, Doucet, & Perez (2003) · Proceedings Ninth IEEE International Conference on Computer Vision · doi:10.1109/iccv.2003.1238473 · Cited by 390
Convolutional Neural Networks Applied to House Numbers Digit Classification
Sermanet, P., Chintala, S., & LeCun, Y. (2012) · arXiv (Cornell University) · doi:10.48550/arxiv.1204.3968 · Cited by 331
An iterative pruning algorithm for feedforward neural networks
Castellano, G., Fanelli, A. M., & Pelillo, M. (1997) · IEEE Transactions on Neural Networks · doi:10.1109/72.572092 · Cited by 295
Fast Training of Convolutional Networks through FFTs
Mathieu, M., Henaff, M., & LeCun, Y. (2013) · arXiv · doi:10.48550/arxiv.1312.5851 · Cited by 273
Fight sample degeneracy and impoverishment in particle filters: A review of intelligent approaches
Li, T., Sun, S., Sattar, T. P., & Corchado, J. M. (2014) · Expert Systems with Applications · doi:10.1016/j.eswa.2013.12.031 · Cited by 257
NIPS 2011 Workshop on Deep Learning and Unsupervised Feature Learning
Cho, K., Raiko, T., & Ilin, A. (2011) · Cited by 245
Performance and Scalability of GPU-Based Convolutional Neural Networks
Strigl, D., Kofler, K., & Podlipnig, S. (2010) · 2010 18th Euromicro Conference on Parallel, Distributed and Network-based Processing · doi:10.1109/pdp.2010.43 · Cited by 240
Channel-level acceleration of deep face representations
Polyak, A., & Wolf, L. (2015) · IEEE Access · doi:10.1109/access.2015.2494536 · Cited by 171
Memory Bounded Deep Convolutional NetworksPreprint
Collins, M. D., & Kohli, P. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1412.1442 · Cited by 164
Resiliency of Deep Neural Networks under Quantization
Sung, W., Shin, S., & Hwang, K. (2015) · arXiv · doi:10.48550/arxiv.1511.06488 · Cited by 132
Self-citationPruning backpropagation neural networks using modern stochastic optimisation techniques
Stepniewski, S. W., & Keane, A. J. (1997) · Neural Computing and Applications · doi:10.1007/bf01501173 · Cited by 45
A Deep Neural Network Compression Pipeline: Pruning, Quantization, Huffman EncodingPreprint
Han, S., Mao, H., & Dally, W. J. (2015) · arXiv (Cornell University) · Cited by 33
Fast ConvNets Using Group-wise Brain DamagePreprint
Lebedev, V., & Lempitsky, V. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1506.02515 · Cited by 29
Research works printed but not linked: 6
- Song Han Jeff Pool John Tran and William Dally. 2015b. Learning both weights and connections for efficient neural network. Advances in Neural Information Processing Systems. 1135--1143. Song Han Jeff Pool John Tran and William Dally. 2015b. Learning both weights and connections for efficient neural network. Advances in Neural Information Processing Systems. 1135--1143.
- 10.1109/IROS.2005.1545119 · doi:10.1109/iros.2005.1545119
- Kazuyuki Nakamura , Ryo Yoshida , Masao Nagasaki , Satoru Miyano , and Tomoyuki Higuchi . 2009 . Parameter estimation of in silico biological pathways with particle filtering towards a petascale computing . In Proceedings of the Pacific Symposium on Biocomputing 14 . 227--238. Kazuyuki Nakamura, Ryo Yoshida, Masao Nagasaki, Satoru Miyano, and Tomoyuki Higuchi. 2009. Parameter estimation of in silico biological pathways with particle filtering towards a petascale computing. In Proceedings of the Pacific Symposium on Biocomputing 14. 227--238.
- 10.5555/2627435.2670313 · doi:10.5555/2627435.2670313
- Tijmen Tieleman and Geoffrey Hinton . 2012 . Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude . COURSERA: Neural Networks for Machine Learning 4 (2012), 2 . Tijmen Tieleman and Geoffrey Hinton. 2012. Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude. COURSERA: Neural Networks for Machine Learning 4 (2012), 2.
- 10.5555/946247.946684 · doi:10.5555/946247.946684
Cited by
Efficient Processing of Deep Neural Networks: A Tutorial and Survey
Sze, V., Chen, Y.-H., Yang, T.-J., & Emer, J. S. (2017) · Proceedings of the IEEE · doi:10.1109/jproc.2017.2761740 · Cited by 4,215
Channel Pruning for Accelerating Very Deep Neural Networks
He, Y., Zhang, X., & Sun, J. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.155 · Cited by 2,647
“Inference-time channel pruning is challenging, as reported by previous works [2, 40].”
ResultA survey on deep learning techniques for image and video semantic segmentation
Garcia-Garcia, A., Orts-Escolano, S., Oprea, S., Villena-Martinez, V., Martinez-Gonzalez, P., & Garcia-Rodriguez, J. (2018) · Applied Soft Computing · doi:10.1016/j.asoc.2018.05.018 · Cited by 1,490
Model Compression and Hardware Acceleration for Neural Networks: A Comprehensive Survey
Deng, B. L., Li, G., Han, S., Shi, L., & Xie, Y. (2020) · Proceedings of the IEEE · doi:10.1109/jproc.2020.2976475 · Cited by 996
Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networks
Liu, K., Dolan-Gavitt, B., & Garg, S. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-00470-5_13 · Cited by 1,055
Metadata
- Authors
- Anwar, S., Hwang, K., & Sung, W.
- Venue
- ACM Journal on Emerging Technologies in Computing Systems
- Published
- 2017-02-09
- Volume
- 13
- Issue
- 3
- Pages
- 1-18
- ISSN
- 1550-4832 (ISSN-L)
- 1550-4840
- OpenAlex
- W2276892413
- Cited by
- 698
- References
- 31
- FWCI
- 30.32
- Type
- journal article
- Language
- en
- Open access
- closed
- Funders
- National Research Foundation of Korea (2015R1A2A1A10056051)
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.