Accelerator-Aware Pruning for Convolutional Neural Networks
Open accessThe DOI matches its Crossref record; 17 of the 17 references it cites were found in a registry or an index.
Abstract
Convolutional neural networks have shown tremendous performance capabilities in computer vision tasks, but their excessive amounts of weight storage and arithmetic operations prevent them from being adopted in embedded environments. One of the solutions involves pruning, where certain unimportant weights are forced to have a value of zero. Many pruning schemes have been proposed, but these have mainly focused on the number of pruned weights, scarcely considering ASIC or FPGA accelerator architectures. When a pruned network is run on an accelerator, the lack of architecture consideration causes some inefficiency problems, including the internal buffer misalignments and load imbalances. This paper proposes a new pruning scheme that reflects accelerator architectures. In the proposed scheme, pruning is performed so that the same number of weights remain for each weight group corresponding to activations fetched simultaneously. In this way, the pruning scheme resolves the inefficiency problems, doubling the accelerator performance. Even with this constraint, the proposed pruning scheme reached a pruning ratio similar to that of the previous unconstrained pruning schemes, not only on AlexNet and VGG16 but also on the state-of-the-art very deep networks, such as ResNet. Furthermore, the proposed scheme demonstrated a comparable pruning ratio on compact networks such as MobileNet and on slimmed networks that were already pruned in a channel-wise manner. In addition to improving the efficiency of previous sparse accelerators, it will be also shown that the proposed pruning scheme can be used to reduce the logic complexity of sparse accelerators.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
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
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2577031 · Cited by 73,472
ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices
Zhang, X., Zhou, X., Lin, M., & Sun, J. (2017) · arXiv · doi:10.48550/arxiv.1707.01083 · Cited by 9,982
ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices
Zhang, X., Zhou, X., Lin, M., & Sun, J. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00716 · Cited by 9,982
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
Iandola, F. N., Han, S., Moskewicz, M. W., Ashraf, K., Dally, W. J., & Keutzer, K. (2016) · arXiv · doi:10.48550/arxiv.1602.07360 · Cited by 6,201 · cited 4×
“3%, the pruning ratio of an unstructured pruning scheme in [5].”
BackgroundInfluentialHan, S., Mao, H., & Dally, W. J. (2015) · arXiv · doi:10.48550/arxiv.1510.00149 · Cited by 4,662
Pruning Filters for Efficient ConvNets
Li, H., Kadav, A., Durdanovic, I., Samet, H., & Graf, H. P. (2016) · arXiv · doi:10.48550/arxiv.1608.08710 · Cited by 2,928
OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks
Sermanet, P., Eigen, D., Zhang, X., Mathieu, M., Fergus, R., & LeCun, Y. (2013) · arXiv · doi:10.48550/arxiv.1312.6229 · Cited by 2,680 · cited 1×
“CONVOLUTIONAL neural networks (CNNs) are attracting interest in the fields of image recognition [1]–[5], object detection [6]–[10], and image segmentation [11].”
BackgroundChannel 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
Optimizing FPGA-based Accelerator Design for Deep Convolutional Neural Networks
Zhang, C., Li, P., Sun, G., Guan, Y., Xiao, B., & Cong, J. (2015) · Proceedings of the 2015 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays · doi:10.1145/2684746.2689060 · Cited by 2,158 · cited 1×
“The architectures proposed in [14]– [17] adopt MWMA-structured PEs, and some of them fetch the activations and weights along the spatial axis [16], [17].”
MethodLearning both Weights and Connections for Efficient Neural Networks
Han, S., Pool, J., Tran, J., & Dally, W. J. (2015) · arXiv · doi:10.48550/arxiv.1506.02626 · Cited by 1,481 · cited 10×
“without constraints [19], [20] while others prune the weights considering the neural network structures.”
BackgroundMethodResultInfluentialGoing Deeper with Convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2014) · arXiv · doi:10.48550/arxiv.1409.4842 · Cited by 1,461
EIE: Efficient Inference Engine on Compressed Deep Neural Network
Han, S., Liu, X., Mao, H., Pu, J., Pedram, A., Horowitz, M. A., & Dally, W. J. (2016) · 2016 ACM/IEEE 43rd Annual International Symposium on Computer Architecture (ISCA) · doi:10.1109/isca.2016.30 · Cited by 1,077
Designing Energy-Efficient Convolutional Neural Networks Using Energy-Aware Pruning
Yang, T.-J., Chen, Y.-H., & Sze, V. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.643 · Cited by 732 · cited 2×
“However, pruning convolutional layers can reduce more energy and realize higher throughput [21].”
BackgroundESE: Efficient Speech Recognition Engine with Sparse LSTM on FPGA
Han, S., Kang, J., Mao, H., Hu, Y., Li, X., Li, Y., Xie, D., Luo, H., Yao, S., Wang, Y., et al. (2017) · Proceedings of the 2017 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays · doi:10.1145/3020078.3021745 · Cited by 591 · cited 7×
“EIE [34], ESE [35], and ZENA [38] adopt SWSA structured PEs to easily skip the pruned weights in the irregular pattern.”
BackgroundMethodInfluentialExploring the Regularity of Sparse Structure in Convolutional Neural Networks
Mao, H., Han, S., Pool, J., Li, W., Liu, X., Wang, Y., & Dally, W. J. (2017) · arXiv · doi:10.48550/arxiv.1705.08922 · Cited by 219 · cited 2×
“in other pruning papers, too [19], [30].”
Background
Cited by
Accelerating Sparse Deep Neural Networks
Mishra, A., Latorre, J. A., Pool, J., Stosic, D., Stosic, D., Venkatesh, G., Yu, C., & Micikevicius, P. (2021) · arXiv · doi:10.48550/arxiv.2104.08378 · Cited by 97
“Additionally, there has been work investigating fine-grained structured sparsity and motivating the need to prune in a fine-grained pattern that is conducive to hardware acceleration [17, 33].”
BackgroundMethodImproving Extreme Low-Bit Quantization With Soft Threshold
Xu, W., Li, F., Jiang, Y., Yong, A., He, X., Wang, P., & Cheng, J. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2022.3216389 · Cited by 32
“Various methods have been proposed to reduce the parameter size and accelerate the inference phase, such as compact model architecture design (in a handcrafted or automatic search way) [3], [4], network pruning [5], [6], [7], [8], knowledge distilling [9], [10], low-rank approximation [11], etc.”
BackgroundMethodFrom Algorithm to Hardware: A Survey on Efficient and Safe Deployment of Deep Neural Networks
Geng, X., Wang, Z., Chen, C., Xu, Q., Xu, K., Jin, C., Gupta, M., Yang, X., Chen, Z., Sabry Aly, M. M., et al. (2025) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2024.3394494 · Cited by 26
Metadata
- Authors
- Kang, H.-J.
- Venue
- IEEE Transactions on Circuits and Systems for Video Technology
- Published
- 2020
- Pages
- 1-1
- ISSN
- 1051-8215 (ISSN-L)
- 1558-2205
- OpenAlex
- W2798275680
- Cited by
- 89
- References
- 17
- FWCI
- 5.81
- Type
- journal article
- Language
- en
- Open access
- green
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.