Abstract
While Capsule Networks overcome many shortcomings of Convolutional Neural Networks by taking spatial hierarchies between features into consideration and providing a new approach to routing between layers, they are sensible towards overfitting. Self-supervised training improves the semantic understanding of a network significantly and improves generalization without requiring additional images. Therefore, self-supervised Capsule Networks are a promising approach to improve learning under data scarcity, which makes the combination interesting for a huge variety of applications. Our approach improves test accuracy by up to 11.7% for small data sets and by up to 11.5% for small and imbalanced data sets. Furthermore, we explore the synergies and characteristics of this innovative method combination and give a general overview on the possibilities of self-supervised Capsule Networks.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Afshar, P., Heidarian, S., Naderkhani, F., Oikonomou, A., Plataniotis, K.N., Mohammadi, A.: COVID-caps: a capsule network-based framework for identification of COVID-19 cases from X-ray images. Pattern Recogn. Lett. 138, 638–643 (2020)
Afshar, P., Naderkhani, F., Oikonomou, A., Rafiee, M.J., Mohammadi, A., Plataniotis, K.N.: MIXCAPS: a capsule network-based mixture of experts for lung nodule malignancy prediction. Pattern Recogn. 116, 107942 (2021)
Albuquerque, I., Naik, N., Li, J., Keskar, N., Socher, R.: Improving out-of-distribution generalization via multi-task self-supervised pretraining. arXiv preprint arXiv:2003.13525 (2020)
Andonie, R.: Extreme data mining: inference from small datasets. Int. J. Comput. Commun. Control 5(3), 280–291 (2010)
Basak, S.C., Grunwald, G.D., Gute, B.D., Balasubramanian, K., Opitz, D.: Use of statistical and neural net approaches in predicting toxicity of chemicals. J. Chem. Inf. Comput. Sci. 40(4), 885–890 (2000)
Bear, D.M., et al.: Learning physical graph representations from visual scenes. arXiv preprint arXiv:2006.12373 (2020)
Chauhan, A., Babu, M., Kandru, N., Lokegaonkar, S.: Empirical study on convergence of capsule networks with various hyperparameters (2018)
Ding, X., Wang, N., Gao, X., Li, J., Wang, X.: Group reconstruction and max-pooling residual capsule network. In: IJCAI, pp. 2237–2243 (2019)
Dombetzki, L.A.: An overview over capsule networks. Network architectures and services (2018)
Du, B., Gao, X., Hu, W., Li, X.: Self-contrastive learning with hard negative sampling for self-supervised point cloud learning. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 3133–3142 (2021)
Duan, Q., Lee, J.: Fast-developing machine learning support complex system research in environmental chemistry. New J. Chem. 44(4), 1179–1184 (2020)
Edstedt, J.: Towards Understanding Capsule Networks (2020)
Fang, C., Shang, Y., Xu, D.: Improving protein gamma-turn inception capsule networks prediction using inception capsule networks. Sci. Rep. 8, 15741 (2018)
Gidaris, S., Bursuc, A., Komodakis, N., Pérez, P., Cord, M.: Boosting few-shot visual learning with self-supervision. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 8059–8068 (2019)
Gidaris, S., Singh, P., Komodakis, N.: Unsupervised representation learning by predicting image rotations. arXiv preprint arXiv:1803.07728 (2018)
Hendrycks, D., Mazeika, M., Kadavath, S., Song, D.: Using self-supervised learning can improve model robustness and uncertainty. arXiv preprint arXiv:1906.12340 (2019)
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
Hu, Y., et al.: An improved algorithm for imbalanced data and small sample size classification. J. Data Anal. Inf. Process. 3(03), 27 (2015)
Huang, R., Li, J., Wang, S., Li, G., Li, W.: A robust weight-shared capsule network for intelligent machinery fault diagnosis. IEEE Trans. Industr. Inf. 16(10), 6466–6475 (2020)
Hutchinson, M.L., Antono, E., Gibbons, B.M., Paradiso, S., Ling, J., Meredig, B.: Overcoming data scarcity with transfer learning. arXiv preprint arXiv:1711.05099 (2017)
Jayaraman, D., Grauman, K.: Learning image representations tied to ego-motion. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1413–1421 (2015)
de Jesus, D.R., Cuevas, J., Rivera, W., Crivelli, S.: Capsule networks for protein structure classification and prediction. arXiv preprint arXiv:1808.07475 (2018)
Jia, B., Huang, Q.: DE-CapsNet: a diverse enhanced capsule network with disperse dynamic routing. Appl. Sci. 10(3), 884 (2020)
Jiménez-Sánchez, A., Albarqouni, S., Mateus, D.: Capsule networks against medical imaging data challenges. In: Stoyanov, D., et al. (eds.) LABELS/CVII/STENT -2018. LNCS, vol. 11043, pp. 150–160. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01364-6_17
Jing, L., Tian, Y.: Self-supervised visual feature learning with deep neural networks: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 43, 4037–4058 (2020)
Kim, J., Jang, S., Park, E., Choi, S.: Text classification using capsules. Neurocomputing 376, 214–221 (2020)
Kim, M., Chi, S.: Detection of centerline crossing in abnormal driving using CapsNet. J. Supercomput. 75(1), 189–196 (2019)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Kitchin, R., Lauriault, T.P.: Small data in the era of big data. GeoJournal 80(4), 463–475 (2014). https://doi.org/10.1007/s10708-014-9601-7
Kolesnikov, A., Zhai, X., Beyer, L.: Revisiting self-supervised visual representation learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1920–1929 (2019)
Kruthika, K., Maheshappa, H., Initiative, A.D.N., et al.: CBIR system using capsule networks and 3D CNN for Alzheimer’s disease diagnosis. Inform. Med. Unlocked 14, 59–68 (2019)
Kumar, A.D.: Novel deep learning model for traffic sign detection using capsule networks. arXiv preprint arXiv:1805.04424 (2018)
LaLonde, R., Bagci, U.: Capsules for object segmentation. arXiv preprint arXiv:1804.04241 (2018)
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)
Lee, H., Hwang, S.J., Shin, J.: Rethinking data augmentation: self-supervision and self-distillation. arXiv preprint arXiv:1910.05872 (2019)
Lee, J.D., Lei, Q., Saunshi, N., Zhuo, J.: Predicting what you already know helps: provable self-supervised learning. arXiv preprint arXiv:2008.01064 (2020)
Li, B., Li, Y., Eliceiri, K.W.: Dual-stream multiple instance learning network for whole slide image classification with self-supervised contrastive learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 14318–14328 (2021)
Li, H., Guo, X., Dai, B., Ouyang, W., Wang, X.: Neural network encapsulation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11215, pp. 266–282. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01252-6_16
Lin, A., Li, J., Ma, Z.: On learning and learned representation with dynamic routing in capsule networks. arXiv preprint arXiv:1810.040412(7) (2018)
Liu, L., Liu, S.S., Yu, M., Zhang, J., Chen, F.: Concentration addition prediction for a multiple-component mixture containing no effect chemicals. Anal. Meth. 7(23), 9912–9917 (2015)
Lu, C., Duan, S., Wang, L.: An improved capsule network based on newly reconstructed network and the method of sharing parameters. In: Lu, H., Tang, H., Wang, Z. (eds.) ISNN 2019. LNCS, vol. 11554, pp. 116–123. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-22796-8_13
Mahendran, A., Thewlis, J., Vedaldi, A.: Self-supervised segmentation by grouping optical-flow. In: Leal-Taixé, L., Roth, S. (eds.) ECCV 2018. LNCS, vol. 11133, pp. 528–534. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-11021-5_31
Mandal, B., Dubey, S., Ghosh, S., Sarkhel, R., Das, N.: Handwritten indic character recognition using capsule networks. In: 2018 IEEE Applied Signal Processing Conference (ASPCON), pp. 304–308. IEEE (2018)
Marchisio, A., Nanfa, G., Khalid, F., Hanif, M.A., Martina, M., Shafique, M.: CapsAttacks: robust and imperceptible adversarial attacks on capsule networks. arXiv preprint arXiv:1901.09878 (2019)
Marcos, D., Volpi, M., Tuia, D.: Learning rotation invariant convolutional filters for texture classification. In: 2016 23rd International Conference on Pattern Recognition (ICPR), pp. 2012–2017. IEEE (2016)
Nair, P., Doshi, R., Keselj, S.: Pushing the limits of capsule networks. arXiv preprint arXiv:2103.08074 (2021)
Noroozi, M., Vinjimoor, A., Favaro, P., Pirsiavash, H.: Boosting self-supervised learning via knowledge transfer. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9359–9367 (2018)
Ohri, K., Kumar, M.: Review on self-supervised image recognition using deep neural networks. Knowl. Based Syst. 224, 107090 (2021)
Ohta, N., Kawai, S., Nobuhara, H.: Analysis and learning of capsule networks robust for small image deformation. In: 2020 International Joint Conference on Neural Networks (IJCNN), pp. 1–7. IEEE (2020)
Ozbulak, G.: Image colorization by capsule networks. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 2150–2158 (2019)
Pasupa, K., Sunhem, W.: A comparison between shallow and deep architecture classifiers on small dataset. In: 2016 8th International Conference on Information Technology and Electrical Engineering (ICITEE), pp. 1–6. IEEE (2016)
Patrick, M.K., Adekoya, A.F., Mighty, A.A., Edward, B.Y.: Capsule networks-a survey. J. King Saud Univ. Comput. Inform. Sci. 34, 1295–1310 (2019)
Peer, D., Stabinger, S., Rodriguez-Sanchez, A.: Limitation of capsule networks. Pattern Recogn. Lett. 144, 68–74 (2021)
Pinto, L., Gupta, A.: Supersizing self-supervision: learning to grasp from 50k tries and 700 robot hours. In: 2016 IEEE International Conference on Robotics and Automation (ICRA), pp. 3406–3413. IEEE (2016)
Raghu, M., Zhang, C., Kleinberg, J., Bengio, S.: Transfusion: understanding transfer learning for medical imaging. arXiv preprint arXiv:1902.07208 (2019)
Sabour, S., Frosst, N., Hinton, G.E.: Dynamic routing between capsules. arXiv preprint arXiv:1710.09829 (2017)
Sabour, S., Tagliasacchi, A., Yazdani, S., Hinton, G.E., Fleet, D.J.: Unsupervised part representation by flow capsules. arXiv preprint arXiv:2011.13920 (2020)
Sayed, N., Brattoli, B., Ommer, B.: Cross and learn: cross-modal self-supervision. In: Brox, T., Bruhn, A., Fritz, M. (eds.) GCPR 2018. LNCS, vol. 11269, pp. 228–243. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-12939-2_17
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)
Sun, K., Yuan, L., Xu, H., Wen, X.: Deep tensor capsule network. IEEE Access 8, 96920–96933 (2020)
Sun, W., et al.: Canonical capsules: self-supervised capsules in canonical pose. In: 35th Conference on Neural Information Processing Systems (2021)
Vijayakumar, T.: Comparative study of capsule neural network in various applications. J. Artif. Intell. 1(01), 19–27 (2019)
Wang, D., Liang, Y., Xu, D.: Capsule network for protein post-translational modification site prediction. Bioinformatics 35(14), 2386–2394 (2019)
Wang, Z., et al.: A novel method for intelligent fault diagnosis of bearing based on capsule neural network. Complexity 2019, 1–17 (2019)
Wu, F., Smith, J.S., Lu, W., Pang, C., Zhang, B.: Attentive prototype few-shot learning with capsule network-based embedding. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12373, pp. 237–253. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58604-1_15
Xi, E., Bing, S., Jin, Y.: Capsule network performance on complex data. arXiv preprint arXiv:1712.03480 (2017)
Xiang, C., Zhang, L., Tang, Y., Zou, W., Xu, C.: MS-CapsNet: a novel multi-scale capsule network. IEEE Signal Process. Lett. 25(12), 1850–1854 (2018)
Xinyi, Z., Chen, L.: Capsule graph neural network. In: International Conference on Learning Representations (2018)
Xu, Q., Chen, K., Zhou, G., Sun, X.: Change capsule network for optical remote sensing image change detection. Remote Sens. 13(14), 2646 (2021)
Yang, M., Zhao, W., Ye, J., Lei, Z., Zhao, Z., Zhang, S.: Investigating capsule networks with dynamic routing for text classification. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 3110–3119 (2018)
Yang, S., et al.: RS-CapsNet: an advanced capsule network. IEEE Access 8, 85007–85018 (2020)
Yang, Y., Xu, Z.: Rethinking the value of labels for improving class-imbalanced learning. arXiv preprint arXiv:2006.07529 (2020)
Yuan, D., Chang, X., Huang, P.Y., Liu, Q., He, Z.: Self-supervised deep correlation tracking. IEEE Trans. Image Process. 30, 976–985 (2020)
Zhang, N., Deng, S., Sun, Z., Chen, X., Zhang, W., Chen, H.: Attention-based capsule networks with dynamic routing for relation extraction. arXiv preprint arXiv:1812.11321 (2018)
Zhang, T., et al.: Intelligent fault diagnosis of machines with small & imbalanced data: a state-of-the-art review and possible extensions. ISA Trans. 119, 152–171 (2022)
Zhang, X., Luo, P., Hu, X., Wang, J., Zhou, J.: Research on classification performance of small-scale dataset based on capsule network. In: Proceedings of the 2018 4th International Conference on Robotics and Artificial Intelligence, pp. 24–28 (2018)
Zhao, T., Liu, Y., Huo, G., Zhu, X.: A deep learning IRIS recognition method based on capsule network architecture. IEEE Access 7, 49691–49701 (2019)
Zhao, W., Ye, J., Yang, M., Lei, Z., Zhang, S., Zhao, Z.: Investigating capsule networks with dynamic routing for text classification. arXiv preprint arXiv:1804.00538 (2018)
Zhao, Y., Birdal, T., Deng, H., Tombari, F.: 3D point capsule networks. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1009–1018 (2019)
Zhu, Z., Peng, G., Chen, Y., Gao, H.: A convolutional neural network based on a capsule network with strong generalization for bearing fault diagnosis. Neurocomputing 323, 62–75 (2019)
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
Wittscher, L., Pigorsch, C. (2022). Exploring Self-supervised Capsule Networks for Improved Classification with Data Scarcity. In: Chen, J.IZ., Tavares, J.M.R.S., Shi, F. (eds) Third International Conference on Image Processing and Capsule Networks. ICIPCN 2022. Lecture Notes in Networks and Systems, vol 514. Springer, Cham. https://doi.org/10.1007/978-3-031-12413-6_4
Download citation
DOI: https://doi.org/10.1007/978-3-031-12413-6_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-12412-9
Online ISBN: 978-3-031-12413-6
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)