Architecture Optimization Techniques for Convolutional Neural Networks: Further Experiments and Insights

Artur Sobolewski, Kamil Szyc

Abstract


In this paper, we have researched implementing convolutional neural network (CNN) models for devices with limited resources, such as smartphones and embedded computers. To optimize the number of parameters of these models, we studied various popular methods that would allow them to operate more efficiently. Specifically, our research focused on the ResNet-101 and VGG-19 architectures, which we modified using techniques specific to model optimization. We aimed to determine which approach would work best for particular requirements for a maximum accepted accuracy drop. Our contribution lies in the comprehensive ablation study, which presents the impact of different approaches on the final results, specifically in terms of reducing model parameters, FLOPS, and the potential decline in accuracy. We explored the feasibility of implementing architecture compression methods that can influence the model's structure. Additionally, we delved into post-training methods, such as pruning and quantization, at various model sparsity levels. This study builds upon our prior research to provide a more comprehensive understanding of the subject matter at hand. 

Full Text:

PDF

References


A. Sobolewski and K. Szyc, “A study of architecture optimization techniques for convolutional neural networks,” in International Conference on Dependability and Complex Systems. Springer, 2023, pp. 273–283. [Online]. Available: https://doi.org/10.1007/978-3-031-37720-4_25

S. Alyamkin, M. Ardi, A. C. Berg, A. Brighton, B. Chen, Y. Chen, H.-P. Cheng, Z. Fan, C. Feng, B. Fu et al., “Low-power computer vision: Status, challenges, and opportunities,” IEEE Journal on Emerging and Selected Topics in Circuits and Systems, vol. 9, no. 2, pp. 411–421, 2019. [Online]. Available: https://doi.org/10.1109/JETCAS.2019.2911899

L. Chen, S. Li, Q. Bai, J. Yang, S. Jiang, and Y. Miao, “Review of image classification algorithms based on convolutional neural networks,” Remote Sensing, vol. 13, no. 22, p. 4712, 2021. [Online]. Available: https://doi.org/10.3390/rs13224712

A. Howard, M. Sandler, G. Chu, L.-C. Chen, B. Chen, M. Tan, W. Wang, Y. Zhu, R. Pang, V. Vasudevan et al., “Searching for mobilenetv3,” in Proceedings of the IEEE/CVF international conference on computer vision, 2019. [Online]. Available: https://doi.org/10.1109/ICCV.2019.00140

X. Zhang, X. Zhou, M. Lin, and J. Sun, “Shufflenet: An extremely efficient convolutional neural network for mobile devices,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2018. [Online]. Available: https://doi.org/10.1109/CVPR.2018.00716

K. Han, Y. Wang, Q. Tian, J. Guo, C. Xu, and C. Xu, “Ghostnet: More features from cheap operations,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2020. [Online]. Available: https://doi.org/10.1109/CVPR42600.2020.00165

K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016. [Online]. Available: https://doi.org/10.1109%2Fcvpr.2016.90

K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” arXiv preprint arXiv:1409.1556, 2014. [Online]. Available: https://doi.org/10.48550/arXiv.1409.1556

S. Mehta, H. Hajishirzi, and M. Rastegari, “Dicenet: Dimension-wise convolutions for efficient networks,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 44, no. 5, pp. 2416–2425, 2020. [Online]. Available: https://doi.org/10.1109/TPAMI.2020.3041871

T. Liang, J. Glossner, L. Wang, S. Shi, and X. Zhang, “Pruning and quantization for deep neural network acceleration: A survey,” Neurocomputing, vol. 461, 2021. [Online]. Available: https://doi.org/10.1016/j.neucom.2021.07.045

I. Rodriguez-Conde, C. Campos, and F. Fdez-Riverola, “Optimized convolutional neural network architectures for efficient on-device vision-based object detection,” Neural Computing and Applications, vol. 34, no. 13, pp. 10 469–10 501, 2022. [Online]. Available: https://doi.org/10.1007/s00521-021-06830-w

H. Qassim, A. Verma, and D. Feinzimer, “Compressed residual- vgg16 cnn model for big data places image recognition,” in 2018 IEEE 8th annual computing and communication workshop and conference (CCWC). IEEE, 2018. [Online]. Available: https://doi.org/10.1109/CCWC.2018.8301729

Z. Li, F. Liu, W. Yang, S. Peng, and J. Zhou, “A survey of convolutional neural networks: Analysis, applications, and prospects,” IEEE transactions on neural networks and learning systems, 2021. [Online]. Available: https://doi.org/10.1109/TNNLS.2021.3084827

C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich, “Going deeper with convolutions,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2015, pp. 1–9. [Online]. Available: https://doi.org/10.1109/CVPR.2015.7298594

F. N. Iandola, S. Han, M. W. Moskewicz, K. Ashraf, W. J. Dally, and K. Keutzer, “Squeezenet: Alexnet-level accuracy with 50x fewer parameters and¡ 0.5 mb model size,” arXiv preprint arXiv:1602.07360, 2016. [Online]. Available: https://doi.org/10.48550/arXiv.1602.07360

M. Lin, Q. Chen, and S. Yan, “Network in network,” arXiv preprint arXiv:1312.4400, 2013. [Online]. Available: https://doi.org/10.48550/arXiv.1312.4400

C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna, “Rethinking the inception architecture for computer vision,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016. [Online]. Available: https://doi.org/10.1109/CVPR.2016.308

F. Chollet, “Xception: Deep learning with depthwise separable convolutions,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2017. [Online]. Available: https://doi.org/10.1109/CVPR.2017.195

A. G. Howard, M. Zhu, B. Chen, D. Kalenichenko, W. Wang, T. Weyand, M. Andreetto, and H. Adam, “Mobilenets: Efficient convolutional neural networks for mobile vision applications,” arXiv preprint arXiv:1704.04861, 2017. [Online]. Available: https://doi.org/10.48550/arXiv.1704.04861

M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L.-C. Chen, “Mobilenetv2: Inverted residuals and linear bottlenecks,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2018. [Online]. Available: https://doi.org/10.1109/CVPR.2018.00474

J. Hu, L. Shen, and G. Sun, “Squeeze-and-excitation networks,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2018. [Online]. Available: https://doi.org/10.1109/TPAMI.2019.2913372

M. Tan and Q. Le, “Efficientnet: Rethinking model scaling for convolutional neural networks,” in International conference on machine learning. PMLR, 2019, pp. 6105–6114. [Online]. Available: https://doi.org/10.48550/arXiv.1905.11946

L. N. Smith and N. Topin, “Super-convergence: Very fast training of neural networks using large learning rates,” in Artificial intelligence and machine learning for multi-domain operations applications, vol. 11006. SPIE, 2019, pp. 369–386. [Online]. Available: https://doi.org/10.48550/arXiv.1708.07120

PyTorch. (2023) Pytorch: Reducelronplateau. PyTorch 2.0 documentation. [Online]. Available: https://pytorch.org/docs/stable/generated/torch.optim.lr_scheduler.ReduceLROnPlateau.html


Refbacks

  • There are currently no refbacks.


International Journal of Electronics and Telecommunications
is a periodical of Electronics and Telecommunications Committee
of Polish Academy of Sciences

eISSN: 2300-1933