Abstract
Siamese Neural Networks (SNN) provide a robust mechanism to learn similarities/dissimilarities between objects of different classes. The distinguishing features learnt by SNNs make them a good candidate for multi-class classification as well. However, the potential of an SNN to create a classification space that has, both higher accuracy and lower inference time, needs to be exploited further. In this paper, we present a novel multi-class classification approach using SNNs by drawing concepts from the Immune Network theory. This bio-inspired strategy aids in injecting class specific characteristics into the SNN architecture, thereby enhancing the classification process. Experimental results conducted on three benchmark datasets indicate that the approach consistently provides higher accuracies and lesser inference times as compared to recent SNN based multi-class classification approaches, indicating its efficacy.
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
Bromley, J., et al.: Signature verification using a “siamese’’ time delay neural network. Int. J. Pattern Recognit. Artif. Intell. 7, 25 (1993)
Jindal, S., Gupta, G., Yadav, M., Sharma, M., Vig, L.: Siamese networks for chromosome classification. In: 2017 IEEE International Conference on Computer Vision Workshops (ICCVW), pp. 72–81 (2017)
Nanni, L., Brahnam, S., Lumini, A., Maguolo, G.: Animal sound classification using dissimilarity spaces. Appl. Sci. 10(23), 8578 (2020). https://www.mdpi.com/2076-3417/10/23/8578
Hindy, H., Tachtatzis, C., Atkinson, R., Bayne, E., Bellekens, X.: Developing a siamese network for intrusion detection systems. In: Proceedings of the 1st Workshop on Machine Learning and Systems, EuroMLSys 2021, pp. 120–126. Association for Computing Machinery, New York (2021). https://doi.org/10.1145/3437984.3458842
Jiang, W., Zhang, L.: Edge-SiamNet and edge-TripleNet: new deep learning models for handwritten numeral recognition. IEICE Trans. Inf. Syst. 103(3), 720–723 (2020)
Zhu, R., Gong, X., Hu, S., Wang, Y.: Power quality disturbances classification via fully-convolutional siamese network and k-nearest neighbor. Energies 12(24), 4732 (2019). https://www.mdpi.com/1996-1073/12/24/4732
Wang, B., Wang, D.: Plant leaves classification: a few-shot learning method based on siamese network. IEEE Access 7, 151754–151763 (2019)
Zhou, M., Tanimura, Y., Nakada, H.: One-shot learning using triplet network with kNN classifier. In: Ohsawa, Y., et al. (eds.) JSAI 2019. AISC, vol. 1128, pp. 227–235. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-39878-1_21
Veal, C., et al.: Doing more with less: similarity neural nets and metrics for small class imbalanced data sets. In: Detection and Sensing of Mines, Explosive Objects, and Obscured Targets XXV, ser. Society of Photo-Optical Instrumentation Engineers (SPIE) Conference Series, vol. 11418, p. 1141802 (2020)
Jerne, N.K.: Towards a network theory of the immune system. Ann. Immunol. 125(1–2), 373–389 (1974). https://pubmed.ncbi.nlm.nih.gov/4142565
Gregory, K., Zemel, R., Salakhutdinov, R.: Siamese neural networks for one-shot image recognition. In: ICML Deep Learning Workshop (2015)
Chopra, S., Hadsell, R., LeCun, Y.: Learning a similarity metric discriminatively, with application to face verification. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2005), vol. 1, pp. 539–546 (2005)
Schroff, F., Kalenichenko, D., Philbin, J.: “Facenet: a unified embedding for face recognition and clustering. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2015, pp. 815–823 (2015)
Chicco, D.: Siamese neural networks: an overview. In: Cartwright, H. (ed.) Artificial Neural Networks. MMB, vol. 2190, pp. 73–94. Springer, New York (2021). https://doi.org/10.1007/978-1-0716-0826-5_3
López, G.Q., Morales, L.A., Niño, L.F.: Immunological computation. In: Autoimmunity: From Bench to Bedside [Internet]. El Rosario University Press (2013). https://www.ncbi.nlm.nih.gov/books/NBK459484
LeCun, Y., Cortes, C.: MNIST handwritten digit database (2010). http://yann.lecun.com/exdb/mnist/
Xiao, H., Rasul, K., Vollgraf, R.: Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms (2017). http://arxiv.org/abs/1708.07747
Clanuwat, T., Bober-Irizar, M., Kitamoto, A., Lamb, A., Yamamoto, K., Ha, D.: Deep Learning for Classical Japanese Literature (2018)
Project Jupyter (2022). https://jupyter.org. Accessed 31 May 2022
Keras: The Python Deep Learning API (2022). https://keras.io. Accessed 31 May 2022
TensorFlow (2022). https://www.tensorflow.org. Accessed 31 May 2022
Dean, T., Boddy, M.: An analysis of time-dependent planning. In: Proceedings of the Seventh AAAI National Conference on Artificial Intelligence, AAAI 1988, pp. 49–54. AAAI Press (1988)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Pandey, S.K., Nair, S.B. (2023). Immuno-Inspired Augmentation of Siamese Neural Network for Multi-class Classification. In: Yan, W.Q., Nguyen, M., Stommel, M. (eds) Image and Vision Computing. IVCNZ 2022. Lecture Notes in Computer Science, vol 13836. Springer, Cham. https://doi.org/10.1007/978-3-031-25825-1_35
Download citation
DOI: https://doi.org/10.1007/978-3-031-25825-1_35
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-25824-4
Online ISBN: 978-3-031-25825-1
eBook Packages: Computer ScienceComputer Science (R0)