Abstract
In this paper, a novel quaternion-valued (QV) capsule module is designed to construct QV capsule networks for image classification. The quaternion algebra is introduced into the capsule networks to effectively capture the external dependencies and internal structural information. Moreover, the QV capsules can enhance the representation of complex information and alleviate the information loss of vanilla capsule networks. Particularly, a non-iterative quaternion routing algorithm is proposed to integrate QV capsules, considering both the membership and the consistency of QV capsules in two stages. Extensive experiments are conducted on classic image datasets, hyperspectral image datasets, and face datasets, which demonstrate that: firstly, the QV capsule network achieves higher classification accuracy, reaching 92.95% in UC Merced Land Use and 95.02% in CIFAR 10; secondly, the QV capsule module is more adaptable to different backbone networks than the vanilla capsule module; finally, the QV capsule network shows high performance with limited training samples.
Similar content being viewed by others
References
Alam M, Samad MD, Vidyaratne L, Glandon A, Iftekharuddin KM (2020) Survey on deep neural networks in speech and vision systems. Neurocomputing 417:302–321. https://doi.org/10.1016/j.neucom.2020.07.053
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). https://doi.org/10.1109/cvpr.2016.90, pp 770–778
Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). https://doi.org/10.1109/cvpr.2015.7298594, pp 1–9
Hinton GE, Krizhevsky A, Wang SD (2011) Transforming auto-encoders. In: Artificial Neural Networks and Machine Learning – ICANN 2011. https://doi.org/10.1007/978-3-642-21735-7_6. Springer, pp 44–51
Sabour S, Frosst N, Hinton GE (2017) Dynamic routing between capsules. In: Proceedings of the 31st international conference on neural information processing systems, pp 3859–3869
Hinton GE, Sabour S, Frosst N (2018) Matrix capsules with EM routing. In: 6th International conference on learning representations, ICLR 2018, Vancouver, BC, Canada, April 30 - May 3, 2018. Conference Track Proceedings. https://openreview.net/forum?id=HJWLfGWRb, pp 1–15
LaLonde R, Xu Z, Irmakci I, Jain S, Bagci U (2021) Capsules for biomedical image segmentation. Med Image Anal 68:89–101908. https://doi.org/10.1016/j.media.2020.101889
Pérez E, Ventura S (2021) Melanoma recognition by fusing convolutional blocks and dynamic routing between capsules. Cancers 13(19):4974–4993. https://doi.org/10.3390/cancers13194974
Parcollet T, Morchid M, Linarès G (2019) Quaternion convolutional neural networks for heterogeneous image processing. In: ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). https://doi.org/10.1109/ICASSP.2019.8682495, pp 8514–8518
Jing B, Prabhu V, Gu A, Whaley J (2021) Rotation-invariant gait identification with quaternion convolutional neural networks (student abstract). In: Proceedings of the AAAI conference on artificial intelligence, vol 35. pp 15805–15806. https://ojs.aaai.org/index.php/AAAI/article/view/17899
Grassucci E, Comminiello D, Uncini A (2021) A quaternion-valued variational autoencoder. In: ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). https://doi.org/10.1109/ICASSP39728.2021.9413859, pp 3310–3314
Xiang M, Dees BS, Mandic DP (2018) Multiple-model adaptive estimation for 3-d and 4-d signals: A widely linear quaternion approach. IEEE Trans Neural Netw Learn Syst 30(1):72–84. https://doi.org/10.1109/TNNLS.2018.2829526
Gu J, Tresp V, Hu H (2021) Capsule network is not more robust than convolutional network. In: 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). https://doi.org/10.1109/CVPR46437.2021.01408, pp 14304–14312
Byerly A, Kalganova T, Dear I (2021) No routing needed between capsules. Neurocomputing 463:545–553. https://doi.org/10.1016/j.neucom.2021.08.064
Huang G, Liu Z, Van Der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). https://doi.org/10.1109/CVPR.2017.243, pp 2261–2269
Chollet F (2017) Xception: Deep learning with depthwise separable convolutions. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). https://doi.org/10.1109/CVPR.2017.195, pp 1800–1807
Zhang T, Qi G, Xiao B, Wang J (2017) Interleaved group convolutions. In: IEEE International conference on computer vision, ICCV 2017, Venice, Italy, October 22-29, 2017. https://doi.org/10.1109/ICCV.2017.469, pp 4383–4392
Zhang X, Zhou X, Lin M, Sun J (2018) Shufflenet: An extremely efficient convolutional neural network for mobile devices. In: 2018 IEEE/CVF conference on computer vision and pattern recognition. https://doi.org/10.1109/CVPR.2018.00716, pp 6848–6856
Ma N, Zhang X, Zheng H-T , Sun J (2018) Shufflenet v2: Practical guidelines for efficient cnn architecture design. In: Proceedings of the European Conference on Computer Vision (ECCV), pp 116–131
Kalyani G, Janakiramaiah B, Karuna A, Prasad L (2021) Diabetic retinopathy detection and classification using capsule networks. Complex Intell Syst. https://doi.org/10.1007/s40747-021-00318-9
Dinani ST, Caragea D (2021) Disaster image classification using capsule networks. In: 2021 International Joint Conference on Neural Networks (IJCNN). https://doi.org/10.1109/IJCNN52387.2021.9534448, pp 1–8
Hsu J-T, Kuo C-H, Chen D-W (2020) Image super-resolution using capsule neural networks. IEEE Access 8:9751–9759. https://doi.org/10.1109/ACCESS.2020.2964292
Sun K, Yuan L, Xu H, Wen X (2020) Deep tensor capsule network. IEEE Access 8:96920–96933. https://doi.org/10.1109/ACCESS.2020.2996282
Gu J, Tresp V (2020) Improving the robustness of capsule networks to image affine transformations. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). https://doi.org/10.1109/CVPR42600.2020.00731, pp 7283–7291
Xiang C, Zhang L, Tang Y, Zou W, Xu C (2018) Ms-capsnet: A novel multi-scale capsule network. IEEE Signal Process Lett 25(12):1850–1854. https://doi.org/10.1109/LSP.2018.2873892
Pucci R, Micheloni C, Foresti G L, Martinel N (2020) Deep interactive encoding with capsule networks for image classification. Multimed Tools Appl 79(43):32243–32258. https://doi.org/10.1007/s11042-020-09455-8
Sun K, Wen X, Yuan L, Xu H (2021) Dense capsule networks with fewer parameters. Soft Comput 25(10):6927–6945. https://doi.org/10.1007/s00500-021-05774-6
Sun G, Ding S, Sun T, Zhang C, Du W (2022) A novel dense capsule network based on dense capsule layers. Appl Intell 52(3):3066–3076. https://doi.org/10.1007/s10489-021-02630-w
Amer M, Maul T (2020) Path capsule networks. Neural Process Lett 52(1):545–559. https://doi.org/10.1007/s00500-021-05774-6
Huang W, Zhou F (2020) Da-capsnet: dual attention mechanism capsule network. Sci Rep 10(1):1–13. https://doi.org/10.1038/s41598-020-68453-w
Peer D, Stabinger S, Rodríguez-Sánchez A (2021) Limitation of capsule networks. Pattern Recog Lett 144:68–74. https://doi.org/10.1016/j.patrec.2021.01.017
Rajasegaran J, Jayasundara V, Jayasekara S, Jayasekara H, Seneviratne S, Rodrigo R (2019) Deepcaps: Going deeper with capsule networks. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). https://doi.org/10.1109/CVPR.2019.01098, pp 10717–10725
Yang S, Lee F, Miao R, Cai J, Chen L, Yao W, Kotani K, Chen Q (2020) Rs-capsnet: An advanced capsule network. IEEE Access 8:85007–85018. https://doi.org/10.1109/ACCESS.2020.2992655
Pucci R, Micheloni C, Martinel N (2021) Self-attention agreement among capsules. In: 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW). https://doi.org/10.1109/ICCVW54120.2021.00035, pp 272–280
Mazzia V, Salvetti F, Chiaberge M (2021) Efficient-CapsNet: capsule network with self-attention routing. Sci Rep 11(1):14634–14647. https://doi.org/10.1038/s41598-021-93977-0
Zhao Z, Cheng S (2021) Capsule networks with non-iterative cluster routing. Neural Netw 143:690–697. https://doi.org/10.1016/j.neunet.2021.07.032
Li Y, Zhao W, Cambria E, Wang S, Eger S (2021) Graph routing between capsules. Neural Netw 143:345–354. https://doi.org/10.1016/j.neunet.2021.06.018
Tygert M, Bruna J, Chintala S, LeCun Y, Piantino S, Szlam A (2016) A mathematical motivation for complex-valued convolutional networks. Neural Comput 28(5):815–825. https://doi.org/10.1162/neco_a_00824
Zhang H, Liu AQ (2021) An optical computing chip executing complex-valued neural network and its on-chip training. In: Katayama R, Takashima Y (eds) ODS 2021: industrial optical devices and systems. https://doi.org/10.1117/12.2597553. SPIE, pp 457–468
Xu F, Zhang J, Fang T, Huang S, Wang M (2018) Synchronous dynamics in neural system coupled with memristive synapse. Nonlinear Dyn 92(3):1395–1402. https://doi.org/10.1007/s11071-018-4134-0
Protachevicz PR, Borges RR, Reis AS, Borges FS, Iarosz KC, Caldas IL, Lameu EL, Macau EEN, Viana RL, Sokolov IM, Ferrari FAS, Kurths J, Batista AM, Lo C-Y, He Y, Lin C-P (2018) Synchronous behaviour in network model based on human cortico-cortical connections. Physiol Meas 39(7):074006. https://doi.org/10.1088/1361-6579/aace91
Guo Y, Gao Z, Liu Y, Li S, Zhu J, Chen P, Liu B-F (2020) Multichannel synchronous hydrodynamic gating coupling with concentration gradient generator for high-throughput probing dynamic signaling of single cells. Anal Chem 92(17):12062–12070. https://doi.org/10.1021/acs.analchem.0c02746
Yin Q, Wang J, Luo X, Zhai J, Jha SK, Shi Y-Q (2019) Quaternion convolutional neural network for color image classification and forensics. IEEE Access 7:20293–20301. https://doi.org/10.1109/ACCESS.2019.2897000
Parcollet T, Morchid M, Linarès G (2020) A survey of quaternion neural networks. Artif Intell Rev 53(4):2957–2982. https://doi.org/10.1007/s10462-019-09752-1
Popa C-A (2018) Learning algorithms for quaternion-valued neural networks. Neural Process Lett 47(3):949–973. https://doi.org/10.1007/s11063-017-9716-1
Zhang A, Tay Y, Zhang S, Chan A, Luu AT, Hui SC, Fu J (2021) Beyond fully-connected layers with quaternions: Parameterization of hypercomplex multiplications with 1/n parameters 9Th international conference on learning representations, ICLR, pp 1–13
Kosiorek A, Sabour S, Teh YW, Hinton GE (2019) Stacked capsule autoencoders. In: Advances in Neural Information Processing Systems, vol 32. https://proceedings.neurips.cc/paper/2019/file/2e0d41e02c5be4668ec1b0730b3346a8-Paper.pdf, pp 1–11
Yang Y, Newsam S (2010) Bag-of-visual-words and spatial extensions for land-use classification. In: Proceedings of the 18th SIGSPATIAL international conference on advances in geographic information systems - GIS’10. https://doi.org/10.1145/1869790.1869829, pp 270–279
Howard AG, Zhu M, Chen B, Kalenichenko D, Wang W, Weyand T, Andreetto M, Adam H (2017) Mobilenets: Efficient convolutional neural networks for mobile vision applications Preprint at arXiv:1704.04861
Sandler M, Howard A, Zhu M, Zhmoginov A, Chen L-C (2018) Mobilenetv2: Inverted residuals and linear bottlenecks. In: 2018 IEEE/CVF conference on computer vision and pattern recognition. https://doi.org/10.1109/CVPR.2018.00474, pp 4510–4520
Huang K-K, Ren C-X, Liu H, Lai Z-R, Yu Y-F, Dai D-Q (2021) Hyperspectral image classification via discriminative convolutional neural network with an improved triplet loss. Pattern Recog 112:107744–107757. https://doi.org/10.1016/j.patcog.2020.107744
Acknowledgements
This work was supported by the National Natural Science Foundation of China (Nos. 11871104 and 12131006). The authors would like to express their gratitude to the reviewers for their insightful remarks and ideas on how to improve the paper’s quality.
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
Zhou, H., Zhang, C., Zhang, X. et al. Image classification based on quaternion-valued capsule network. Appl Intell 53, 5587–5606 (2023). https://doi.org/10.1007/s10489-022-03849-x
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-022-03849-x