Abstract
Capsule Network presents a new generation of neural networks in the deep learning field. It shows its potential in image classification by grouping features into capsules and using parts to make the whole, which is accomplished through the use of dynamic routing algorithm to route between capsules. Nonetheless, the original Capsule Network is inefficient for complex images due to its limited ability to extract features and its tendency to explain everything in the image. To address the aforementioned concerns, we propose EMG-CapsNet an improved Capsule Network that uses two parallel convolutional layers, one of them with the Exponential Linear Unit activation function. Then we use a gate layer to control the information passed to the next layer. EMG-CapsNet shows better performance approximately 5% compared with the original Capsule Network on the CIFAR-10 dataset. Moreover, the Exponential Linear Unit function allows faster convergence.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Sabour, S., Frosst, N., Hinton, G.E.: Dynamic routing between capsules. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, pp. 3859–3869 (2017)
Wan, L., Zeiler, M., Zhang, S., Cun, Y.L., Fergus, R.: Regularization of neural networks using dropconnect. In: International Conference on Machine Learning, pp. 1058–1066. PMLR (2013)
Krizhevsky, A., Hinton, G., et al.: Learning multiple layers of features from tiny images (2009)
Kim, J., Jang, S., Park, E., Choi, S.: Text classification using capsules. Neurocomputing 376, 214–221 (2020)
Hinton, G.E., Krizhevsky, A., Wang, S.D.: Transforming auto-encoders. In: Honkela, T., Duch, W., Girolami, M., Kaski, S. (eds.) ICANN 2011. LNCS, vol. 6791, pp. 44–51. Springer, Heidelberg (2011). https://doi.org/10.1007/978-3-642-21735-7_6
Yang, S., et al.: RS-CapsNet: an advanced capsule network. IEEE Access 8, 85007–85018 (2020)
Shahroudnejad, A., Afshar, P., Plataniotis, K.N., Mohammadi, A.: Improved explainability of capsule networks: relevance path by agreement. In: 2018 IEEE Global Conference on Signal and Information Processing (GlobalSIP), pp. 549–553. IEEE (2018)
Hinton, G.E., Sabour, S., Frosst, N.: Matrix capsules with EM routing. In: International Conference on Learning Representations (2018)
Kosiorek, A., Sabour, S., Teh, Y.W., Hinton, G.E.: Stacked capsule autoencoders. In: Advances in Neural Information Processing Systems, vol. 32, pp. 15512–15522 (2019)
Rajasegaran, J., Jayasundara, V., Jayasekara, S., Jayasekara, H., Seneviratne, S., Rodrigo, R.: DeepCaps: going deeper with capsule networks. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10725–10733 (2019)
Chen, J., Liu, Z.: Mask dynamic routing to combined model of deep capsule network and U-Net. IEEE Trans. Neural Netw. Learn. Syst. 31(7), 2653–2664 (2020)
Liu, J., et al.: FSC-CapsNet: fractionally-strided convolutional capsule network for complex data. In: 2019 International Joint Conference on Neural Networks (IJCNN), pp. 1–7. IEEE (2019)
Ding, X., Wang, N., Gao, X., Li, J., Wang, X.: Group reconstruction and max-pooling residual capsule network. In: IJCAI, pp. 2237–2243 (2019)
Nguyen, H.P., Ribeiro, B.: Advanced capsule networks via context awareness. In: Tetko, I.V., Kurková, V., Karpov, P., Theis, F. (eds.) ICANN 2019. LNCS, vol. 11727, pp. 166–177. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-30487-4_14
Yi, S., Ma, H., Li, X.: Modified capsule network for object classification. In: Zhao, Y., Barnes, N., Chen, B., Westermann, R., Kong, X., Lin, C. (eds.) ICIG 2019. LNCS, vol. 11901, pp. 256–266. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-34120-6_21
Ahmed, K., Torresani, L.: Star-caps: capsule networks with straight-through attentive routing. In: Advance Neural Information Processing System, vol. 32, pp. 9101–9110 (2019)
Gagana, B., Ujjwal Athri, H.A., Natarajan, S.: Activation function optimizations for capsule networks. In: 2018 International Conference on Advances in Computing, Communications and Informatics (ICACCI), pp. 1172–1178. IEEE (2018)
Canqun Xiang, L., Zhang, Y.T., Zou, W., Chen, X.: MS-CapsNet: a novel multi-scale capsule network. IEEE Signal Process. Lett. 25(12), 1850–1854 (2018)
El Alaoui-Elfels, O., Gadi, T.: From auto-encoders to capsule networks: a survey. In: E3S Web of Conferences, vol. 229, p. 01003. EDP Sciences (2021)
Clevert, D.-A., Unterthiner, T., Hochreiter, S.: Fast and accurate deep network learning by exponential linear units (ELUS). arXiv preprint arXiv:1511.07289 (2015)
Zhao, Z., Kleinhans, A., Sandhu, G., Patel, I., Unnikrishnan, K.P.: Fast inference in capsule networks using accumulated routing coefficients. DeepAI, 15 April 2019
Zhao, Z., Kleinhans, A., Sandhu, G., Patel, I., Unnikrishnan, K.P.: Capsule networks with max-min normalization. DeepAI, 22 March 2019
Author information
Authors and Affiliations
Corresponding authors
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
El Alaoui-Elfels, O., Gadi, T. (2022). EMG-CapsNet: Elu Multiplication Gate Capsule Network for Complex Images Classification. In: Abraham, A., et al. Proceedings of the 13th International Conference on Soft Computing and Pattern Recognition (SoCPaR 2021). SoCPaR 2021. Lecture Notes in Networks and Systems, vol 417. Springer, Cham. https://doi.org/10.1007/978-3-030-96302-6_9
Download citation
DOI: https://doi.org/10.1007/978-3-030-96302-6_9
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-96301-9
Online ISBN: 978-3-030-96302-6
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)