Abstract
Deep neural networks (DNN) have achieved great success in machine learning due to their powerful ability to learn and present knowledge. However, models of such DNN often have massive trainable parameters, which lead to big resource burden in practice. As a result, reducing the amount of parameters and preserving its competitive performance are always critical tasks in the field of DNN. In this paper, we focused on one type of convolution neural network that has many repeated or same-structure convolutional layers. Residual net and its variants are widely used, making the deeper model easy to train. One type block of such a model contains two convolutional layers, and each block commonly has two trainable parameter layers. However, we used only one layer of trainable parameters in the block, which means that the two convolutional layers in one block shared one layer of trainable parameters. We performed extensive experiments for different architectures of the Residual Net with trainable parameter sharing on the CIFAR-10, CIFAR-100, and ImageNet datasets. We found that the model with trainable parameter sharing can obtain fewer errors on the training datasets and had a very close recognition accuracy (within 0.5%), compared to the original models. The parameters of the new model were reduced by more than 1/3 of the total of the original.
Similar content being viewed by others
References
Cireşan D, Meier U, Schmidhuber J (2012) Multi-column deep neural networks for image classification. ArXiv preprint arXiv:1202.2745
Girshick R, Donahue J, Darrell T, Malik J (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition (pp 580–587)
Krizhevsky A, Sutskever I, Hinton GE (2012) ImageNet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp 1097–1105
Shrikumar A, Greenside P, Kundaje A (2017) Learning important features through propagating activation differences. ArXiv preprint arXiv:1704.02685
Zeiler MD, Fergus R (2014) Visualizing and understanding convolutional networks. In: European conference on computer vision, pp 818–833. Springer, Cham
Zhou B, Khosla A, Lapedriza A, Oliva A, Torralba A (2016) Learning deep features for discriminative localization. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2921–2929
Bach S, Binder A, Montavon G, Klauschen F, Müller KR, Samek W (2015) On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation. PLoS ONE 10(7):e0130140
Zintgraf LM, Cohen TS, Adel T, Welling M (2017) Visualizing deep neural network decisions: prediction difference analysis. ArXiv preprint arXiv:1702.04595
Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. ArXiv preprint arXiv:1409.1556
Zagoruyko S, Komodakis N (2016) Wide residual networks. ArXiv preprint arXiv:1605.07146
Yosinski J, Clune J, Nguyen A, Fuchs T, Lipson H (2015) Understanding neural networks through deep visualization. ArXiv preprint arXiv:1506.06579
Ren S, He K, Girshick R, Sun J (2015) Faster r-cnn: Towards real-time object detection with region proposal networks. In: Advances in neural information processing systems, pp 91–99
Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3431–3440
Liu Z, Li J, Shen Z, Huang G, Yan S, Zhang C (2017) Learning efficient convolutional networks through network slimming. In: 2017 IEEE international conference on computer vision (ICCV), pp 2755–2763. IEEE
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770–778
Krizhevsky A, Nair V, Hinton G (2010) Cifar-10 (Canadian Institute for Advanced Research). http://www.cs.toronto.edu/kriz/cifar.html
Chrabaszcz P, Loshchilov I, Hutter F (2017) A downsampled variant of ImageNet as an alternative to the CIFAR datasets. ArXiv preprint arXiv:1707.08819
Lowe DG (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vision 60(2):91–110
Belue LM, Bauer KW Jr (1995) Determining input features for multilayer perceptrons. Neurocomputing 7(2):111–121
LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436
Celik MU, Sharma G, Tekalp AM, Saber E (2002) Reversible data hiding. In: Proceedings international conference on image processing, vol 2, p II. IEEE
LeCun Y, Boser BE, Denker JS, Henderson D, Howard RE, Hubbard WE, Jackel LD (1990) Handwritten digit recognition with a back-propagation network. In: Advances in neural information processing systems, pp 396–404
Lin M, Chen Q, Yan S (2013) Network in network. ArXiv preprint arXiv:1312.4400
Huang G, Liu Z, Van Der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. In: CVPR, vol 1(2), p 3
Hornic K (1989) Multilayer feedforward networks are universal approximators. Neural Netw 2(5):359–366
Leshno M, Vladimir YL, Pinkus A et al (1991) Multilayer feedforward networks with a nonpolynomial activation function can approximate any function. Neural Netw 6(6):861–867
Heaton J, Goodfellow I, Bengio Y, Courville A (2017) Deep learning. Genet Program Evolvable Mach. https://doi.org/10.1007/s10710-017-9314-z
Zhang X, Luo H, Fan X, Xiang W, Sun Y, Xiao Q et al (2017) Alignedreid: surpassing human-level performance in person re-identification. ArXiv preprint arXiv:1711.08184
Ioffe S, Szegedy C (2015) Batch normalization: Accelerating deep network training by reducing internal covariate shift. ArXiv preprint arXiv:1502.03167
Lee CY, Xie S, Gallagher P, Zhang Z, Tu Z (2015). Deeply-supervised nets. In: Artificial intelligence and statistics, pp 562–570
Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S et al (2015) ImageNet large scale visual recognition challenge. Int J Comput Vision 115(3):211–252
Acknowledgements
This work was sponsored by Natural Science Foundation of Chongqing (No. E021D2019034), Chongqing Education Commission (No. E010J2019025), NSFC project (No. 61771146, 61375122), and in part by Shanghai Science and Technology Development Funds (No. 13dz2260200, 13511504300).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Dai, D., Yu, L. & Wei, H. Parameters Sharing in Residual Neural Networks. Neural Process Lett 51, 1393–1410 (2020). https://doi.org/10.1007/s11063-019-10143-4
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11063-019-10143-4