Abstract
A significant amount of Deep Learning research deals with the reduction of network complexity. In most scenarios the preservation of very high performance has priority over size reduction. However, when dealing with embedded systems, the limited amount of resources forces a switch in perspective. In fact, being able to dramatically reduce complexity could be a stronger requisite for overall feasibility than excellent performance. In this paper we propose a simple to implement yet effective method to largely reduce the size of Convolutional Neural Networks with minimal impact on their performance. The key idea is to assess the relevance of each kernel with respect to a representative dataset by computing the output of its activation function and to trim them accordingly. The resulting network becomes small enough to be adopted on embedded hardware, such as smart cameras or lightweight edge processing units. In order to assess the capability of our method with respect to real-world scenarios, we adopted it to shrink two different pre-trained networks to be hosted on general purpose low-end FPGA hardware to be found in embedded cameras. Our experiments demonstrated both the overall feasibility of the method and its superior performance when compared with similar size-reducing techniques introduced in recent literature.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
this is actually the case for 1D convolutional layers, but the extension to 2D layers is straightforward.
References
Blalock, D., et al.: What is the state of neural network pruning? In: arXiv preprint arXiv:2003.03033 (2020)
Cao, S., et al.: ThinNet: an efficient convolutional neural network for object detection. In: 2018 24th International Conference on Pattern Recognition (ICPR), pp. 836–841 (2018). https://doi.org/10.1109/ICPR.2018.8545809
Courbariaux, M., Bengio, Y., David, J.P.: Training deep neural networks with low precision multiplications. In: arXiv preprint arXiv:1412.7024 (2014)
Garg, I., Panda, P., Roy, K.: A low effort approach to structured CNN design using PCA. IEEE Access 8, 1347–1360 (2019)
Gasparetto, A. et al.: Cross-dataset data augmentation for convolutional neural networks training. In: vol. 2018-August, pp. 910–915 (2018). https://doi.org/10.1109/ICPR.2018.8545812
Han, S., Mao, H., Dally, W.J.: Deep compression: compressing deep neural networks with pruning, trained quantization and huffman coding. In: arXiv preprint arXiv:1510.00149 (2015)
Han, S., et al.: Learning both weights and connections for efficient neural networks. arXiv preprint arXiv:1506.02626 (2015)
He, Y., et al.: Filter pruning via geometric median for deep convolutional neural networks acceleration. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4340–4349 (2019)
Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. In: arXiv preprint arXiv:1503.02531 (2015)
Howard, A.G., et al.: Mobilenets: Efficient convolutional neural networks for mobile vision applications. In: arXiv preprint arXiv:1704.04861 (2017)
Hu, H., et al.: Network trimming: a data-driven neuron pruning approach towards efficient deep architectures. In: arXiv preprint arXiv:1607.03250 (2016)
Iandola, F.N., et al.: SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and \(<\) 0.5 MB model size (2016)
Jahanshahi, A.: TinyCNN: a tiny modular CNN accelerator for embedded FPGA. In: arXiv preprint arXiv:1911.06777 (2019)
Jin, J., Dundar, A., Culurciello, E.: Flattened convolutional neural networks for feedforward acceleration. In: arXiv preprint arXiv:1412.5474 (2014)
Krizhevsky, A., Nair, V., Hinton, G.: CIFAR-10 (Canadian Institute for Advanced Research). http://www.cs.toronto.edu/~kriz/cifar.html
Li, H., et al.: Pruning filters for efficient convnets. In: arXiv preprint arXiv:1608.08710 (2016)
Lin, M., et al.: Hrank: Filter pruning using high-rank feature map. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1529–1538 (2020)
Lin, S., et al.: Towards optimal structured cnn pruning via generative adversarial learning (2019)
Liu, Z., et al.: Learning efficient convolutional networks through network slimming. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2736–2744 (2017)
Liu, Z., et al.: Rethinking the value of network pruning. In: arXiv preprint arXiv:1810.05270 (2018)
Pistellato, M., Bergamasco, F., Albarelli, A., Torsello, A.: Dynamic optimal path selection for 3D triangulation with multiple cameras. In: Murino, V., Puppo, E. (eds.) ICIAP 2015. LNCS, vol. 9279, pp. 468–479. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-23231-7_42
Pistellato, M., et al.: Robust joint selection of camera orientations and feature projections over multiple views, pp. 3703–3708 (2016). https://doi.org/10.1109/ICPR.2016.7900210
Qiu, J., et al.: Going deeper with embedded fpga platform for convolutional neural network. In: Proceedings of the 2016 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays (2016)
Rastegari, M., Ordonez, V., Redmon, J., Farhadi, A.: XNOR-Net: Imagenet classification using binary convolutional neural networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 525–542. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46493-0_32
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition (2014). CoRR abs/1409.1556
Suau, X., Apostoloff, N., et al.: Filter distillation for network compression. In: 2020 IEEE Winter Conference on Applications of Computer Vision (WACV). IEEE, pp. 3129–3138 (2020)
Sze, V., et al.: Efficient processing of deep neural networks: a tutorial and survey. In: Proceedings of the IEEE, vol. 105(12) (2017)
Zhang, C., Patras, P., Haddadi, H.: Deep learning in mobile and wireless networking: a survey. In: IEEE Communications surveys & tutorials, vol. 21 no. 3, pp. 2224–2287 (2019)
Zhang, X., et al.: Shuffenet: an extremely efficient convolutional neural network for mobile devices. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 848–6856 (2018)
Zhu, M., Gupta, S.: To prune, or not to prune: exploring the efficacy of pruning for model compression. In: arXiv preprint arXiv:1710.01878 (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Ressi, D., Pistellato, M., Albarelli, A., Bergamasco, F. (2022). A Relevance-Based CNN Trimming Method for Low-Resources Embedded Vision. In: Bandini, S., Gasparini, F., Mascardi, V., Palmonari, M., Vizzari, G. (eds) AIxIA 2021 – Advances in Artificial Intelligence. AIxIA 2021. Lecture Notes in Computer Science(), vol 13196. Springer, Cham. https://doi.org/10.1007/978-3-031-08421-8_20
Download citation
DOI: https://doi.org/10.1007/978-3-031-08421-8_20
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-08420-1
Online ISBN: 978-3-031-08421-8
eBook Packages: Computer ScienceComputer Science (R0)