An Improved Routing based Capsule Network for Hyperspectral Image Classification


  • B. Thiyagarajan Research Scholar, Department of Computer Science and Engineering, Puducherry Technological University, Puducherry – 605014, India.
  • M. Thenmozhi Associate Professor, Department of Computer Science and Engineering, Puducherry Technological University, Puducherry – 605014, India.
  • K. Revathy PG Student, Department of Computer Science and Engineering, Puducherry Technological University, Puducherry – 605014, India.


Capsule network, Routing algorithm, Improved Routing algorithm, image classification, Convolution Neural Network, Deep Learning


Capsule networks have emerged as a solution to the limitations faced by convolutional neural networks. This innovative architecture focuses on encoding features and capturing spatial relationships within images. Instead of employing max pooling, capsule networks introduce a dynamic routing process. The Capsule network is trained to classify each pixel in a hyperspectral image to predefined categories with suitable loss functions and techniques for optimization. By effectively modeling the complex information embodied in hyperspectral data, capsule networks have the potential to improve the accuracy of hyperspectral image classification, making them an invaluable tool for applications such as remote sensing that rely significantly on spectral information. However, the original three-layer capsule network with dynamic routing exhibits subpar performance on intricate datasets like CIFAR-10/100, SVHN and PaviaU HIS dataset, primarily due to the computationally intensive nature of the dynamic routing algorithm. To tackle these challenges, an enhanced capsule network has been proposed, integrating a dense block layer and an "Improved Routing" algorithm. This improved capsule network configuration has undergone testing on CIFAR-10 and SVHN datasets, resulting in notable enhancements such as improved accuracy, reduced loss rates, and decreased time complexity.


Download data is not yet available.


Zhang Y, Li W, Zhang M, Qu Y, Tao R, Qi H. Topological structure and semantic information transfer network for cross-scene hyperspectral image classification. IEEE Transact Neural Networks Learn Syst 2021. In press.

A. Krizhevsky, I. Sutskever, and G. E. Hinton, ‘‘ImageNet classification with deep convolutional neural networks,’’ in Proc. Adv. Neural Inf. Pro- cess. Syst., vol. 25, 2012, pp. 1097–1105.

S. Huang, F. Lee, R. Miao, Q. Si, C. Lu, and Q. Chen, ''A deep convolutional neural network architecture for interstitial lung disease pattern classification,'' Med. Biol. Eng. Comput., vol. 58, no. 4, pp. 725–737, Jan. 2020.

K. He, X. Zhang, S. Ren, and J. Sun, ‘‘Deep residual learning for image recognition,’’ in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun. 2016, pp. 770–778.

L. Xie, F. Lee, L. Liu, K. Kotani, and Q. Chen, ''Scene recognition: A comprehensive survey,'' Pattern Recognit., vol. 102, Jun. 2020, Art. no. 107205.

L. Xie, F. Lee, L. Liu, Z. Yin, and Q. Chen, ‘‘Hierarchical coding of convolutional features for scene recognition,’’ IEEE Trans. Multimedia, vol. 22, no. 5, pp. 1182–1192, May 2020.

J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, ‘‘You only look once: Unified, real-time object detection,’’ in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun. 2016, pp. 779–788.

J. Cai, F. Lee, S. Yang, C. Lin, H. Chen, K. Kotani, and Q. Chen, ''Pedes- train as points: An improved anchor-free method for centre-based pedestrian detection,'' IEEE Access, vol. 8, pp. 179666–179677, Sep. 2020.

E. Shelhamer, J. Long, and T. Darrell, ‘‘Fully convolutional networks for semantic segmentation,’’ IEEE Trans. Pattern Anal. Mach. Intell., vol. 39, no. 4, pp. 640–651, Apr. 2017.

Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, ‘‘Gradient-based learn- ing applied to document recognition,’’ Proc. IEEE, vol. 86, no. 11, pp. 2278–2324, Nov. 1998.

C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan,V. Vanhoucke, and A. Rabinovich, ‘‘Going deeper with convolutions,’’ in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun. 2015, pp. 1–9.

G. E. Hinton, A. Krizhevsky, and S. D. Wang, ''Transforming auto-encoders,'' in Proc. Int. Conf. Artif. Neural Netw., 2011, pp. 44–51.

S. Sabour, N. Frosst, and G. E. Hinton, ‘‘Dynamic routing between capsules,’’ in Proc. 31st Int. Conf. Neural Inf. Process. Syst., 2017, pp. 3859–3869.

T. Hahn, M. Pyeon, and G. Kim, ‘‘Self-routing capsule networks,’’ in Proc. Adv. Neural Inf. Process. Syst., 2019, pp. 7656–7665.

Y. LeCun, C. Cortes, and C. J. Burges. (1998). The MNIST Database of Handwritten Digits. [Online]. Available:

S. S. R. Phaye, A. Sikka, A. Dhall, and D. R. Bathula, ‘‘Multi-level dense capsule networks,’’ in Proc. Asian Conf. Comput. Vis., Dec. 2018, pp. 577–592.

G. Huang, Z. Liu, L. Van Der Maaten, and K. Q. Weinberger, ‘‘Densely connected convolutional networks,’’ in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jul. 2017, pp. 4700–4708.

X. Wang, R. Girshick, A. Gupta, and K. He, ‘‘Non-local neural networks,’’ in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit., Jun. 2018, pp. 7794–7803.

S. Woo, J. Park, J. Y. Lee, and I. S. Kweon, ‘‘CBAM: Convolutional block attention module,’’ in Proc. Eur. Conf. Comput. Vis. (ECCV), 2018, pp. 3–19.

J. Hu, L. Shen, and G. Sun, ‘‘Squeeze-and-excitation networks,’’ in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit., Jun. 2018, pp. 7132–7141.

S. Anwar, K. Hwang, and W. Sung, ''Structured pruning of deep convolutional neural networks,'' ACM J. Emerg. Technol. Comput. Syst., vol. 13, no. 3, pp. 1–18, 2017.

J.-H. Luo, J. Wu, and W. Lin, ‘‘ThiNet: A filter level pruning method for deep neural network compression,’’ in Proc. IEEE Int. Conf. Comput. Vis. (ICCV), Oct. 2017, pp. 5058–5066.

N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, and

R. Salakhutdinov, ‘‘Dropout: A simple way to prevent neural networks from overfitting,’’ J. Mach. Learn. Res., vol. 15, no. 1, pp. 1929–1958, 2014.

S. Yang, F. Lee, R. Miao, J. Cai, L. Chen, W. Yao, K. Kotani, and Q. Chen, ‘‘RS-CapsNet: An advanced capsule network,’’ IEEE Access, vol. 8, pp. 85007–85018, 2020.

Sara Sabour, Nicholas Frosst and Geoffrey E Hinton, “Dynamic Routing Between Capsules” in arXiv,

Geoffrey Hinton, Sara Sabour and Nicholas Frosst“ Matrix Capsules with EM Routing” Published as a conference paper at ICLR 2018, vol. 15,

BodhisatwaMandal, SwarnenduGhosh, RiteshSarkhel, Nibaran Das, MitaNasipuri "Using dynamic routing to extract intermediate features for developing scalable capsule network" in the international conference on advanced computational and communication, 2018

S. K. Sahu, P. Kumar and A. P. Singh, "Dynamic Routing Using Inter Capsule Routing Protocol between Capsules," 2018 UKSim-AMSS 20th International Conference on Computer Modelling and Simulation (UKSim), Cambridge, UK, 2018, pp. 1-5, doi: 10.1109/UKSim.2018.00012.

J. Chen and Z. Liu, "Mask Dynamic Routing to Combined Model of Deep Capsule Network and U-Net," in IEEE Transactions on Neural Networks and Learning Systems, vol. 31, no. 7, pp. 2653-2664, July 2020, doi: 10.1109/TNNLS.2020.2984686.

F. M. Saif, T. Imtiaz, S. Rifat, C. Shahnaz, W. -P. Zhu and M. O. Ahmad, "CapsCovNet: A Modified Capsule Network to Diagnose COVID-19 From Multimodal Medical Imaging," in IEEE Transactions on Artificial Intelligence, vol. 2, no. 6, pp. 608-617, Dec. 2021, doi: 10.1109/TAI.2021.3104791.

W. Wang, F. Lee, S. Yang and Q. Chen, "An Improved Capsule Network Based on Capsule Filter Routing," in IEEE Access, vol. 9, pp. 109374-109383, 2021, doi: 10.1109/ACCESS.2021.3102489.

Mandal, B., Sarkhel, R., Ghosh, S., Das, N., &Nasipuri, M. (2021). Two-phase Dynamic Routing for Micro and Macro-level Equivariance in Multi-Column Capsule Networks. Pattern Recognition, 109.

R. Zeng and Y. Song, "A Fast Routing Capsule Network With Improved Dense Blocks," in IEEE Transactions on Industrial Informatics, vol. 18, no. 7, pp. 4383-4392, July 2022, doi: 10.1109/TII.2021.3128412.

Li, H., Yang, S. & Wang, W. Improved capsule routing for weakly labelled sound event detection. J AUDIO SPEECH MUSIC PROC. 2022, 5 (2022).

Gao Huang, Zhuang Liu, Laurens van der Maaten, Kilian Q. Weinberger “Densely Connected Convolutional Networks” 2018,activity%20in%20the%20boat%20capsule.

T. Liu, X. Lin, W. Jia, M. Zhou, and W. Zhao, ``Regularized attentive capsule network for overlapped relation extraction,'' in Proc. 28th Int.Conf. Comput. Linguistics, 2020, pp. 6388_6398.

H. Lin, F. Meng, J. Su, Y. Yin, Z. Yang, Y. Ge, J. Zhou, and J. Luo, ``Dynamic context-guided capsule network for multimodal machine translation,'' in Proc. 28th ACM Int. Conf. Multimedia, Oct. 2020, pp. 1320_1329.

] M. Edraki, N. Rahnavard, and M. Shah, ``Subspace capsule network,'' in Proc. AAAI Conf. Artif. Intell., Apr. 2020, vol. 34, no. 7, pp. 10745_10753.

F. Wu, J. S. Smith, W. Lu, C. Pang, and B. Zhang, ``Attentive prototype few-shot learning with capsule network-based embedding,'' in Proc. Eur.Conf. Comput. Vis., Aug. 2020, pp. 237_253.

S. Sabour, A. Tagliasacchi, S. Yazdani, G. E. Hinton, and D. J. Fleet, ``Unsupervised part representation by _ow capsules,'' 2020,

arXiv:2011.13920. [Online]. Available:

A. Jaiswal, W. AbdAlmageed, Y. Wu, and P. Natarajan, ``CapsuleGAN: Generative adversarial capsule network,'' in Proc. Eur. Conf. Comput.Vis. (ECCV), 2018, pp. 526_535.

Y. Le, C. He, M. Chen, Y. Wu, X. He, and B. Zhou, ``Learning to predict charges for legal judgment via self-attentive capsule network,'' Frontiers Artif. Intell. Appl., vol. 325, pp. 1802_1809, May 2020.

J. Yang, P. Zhao, Y. Rong, C. Yan, C. Li, H. Ma, and J. Huang, ``Hierarchical graph capsule network,'' 2020, arXiv:2012.08734. [Online]. Available:




How to Cite

Thiyagarajan, B. ., Thenmozhi, M. ., & Revathy, K. . (2023). An Improved Routing based Capsule Network for Hyperspectral Image Classification. International Journal of Intelligent Systems and Applications in Engineering, 12(2), 79–89. Retrieved from



Research Article