Abstract
Siamese neural networks are an effective architecture for automatic construction of vector representations of objects, by whose comparison it is possible to solve the classification problem. The mentioned approach utilizes the training selection more effectively; it is capable of distinguishing classes by a small number of samples, and it can learn with a dynamic number of classes. We propose an improved method of tuning the Siamese neural networks for solving the classification problem, that uses information about the class hierarchy. The advantage of the mentioned method is demonstrated in examples of image and text classifications.
Similar content being viewed by others
References
Chopra, S., Hadsell, R., LeCun, Y.: Learning a similarity metric discriminatively, with application to face verification. 2005 IEEE computer society conference on computer vision and pattern recognition (CVPR’05). vol. 1. IEEE, pp. 539–546 (2005). https://doi.org/10.1109/CVPR.2005.202
Chen, W., et al.: Beyond triplet loss: a deep quadruplet network for person re-identification. Proceedings of the IEEE conference on computer vision and pattern recognition., pp. 403–412 (2017)
Ciraco, M., Rogalewski, M., Weiss, G.: Improving classifier utility by altering the misclassification cost ratio. Proceedings of the 1st international workshop on Utility-based data mining., pp. 46–52 (2005). https://doi.org/10.1145/1089827.1089833
Liang, J.: Confusion matrix: Machine learning. POGIL Activity Clgh. 3(4), (2022)
Masters, D., Luschi, C.: Revisiting small batch training for deep neural networks. (2018). arXiv preprint arXiv:1804.07612
Bender, M.A., et al.: Lowest common ancestors in trees and directed acyclic graphs. J. Algorithms 57(2), 75–94 (2005)
Dong, X., Shen, J.: Triplet loss in siamese network for object tracking. Proceedings of the European conference on computer vision (ECCV)., pp. 459–474 (2018)
Krizhevsky, A., et al.: Learning multiple layers of features from tiny images (2009)
Memon, S.A., Khan, K.A., Naveed, H.: HECNet: a hierarchical approach to enzyme function classification using a Siamese Triplet Network. Bioinformatics 36(17), 4583–4589 (2020). https://doi.org/10.1093/bioinformatics/btaa536
Barz, B., Denzler, J.: Hierarchy-based image embeddings for semantic image retrieval. 2019 IEEE winter conference on applications of computer vision (WACV). IEEE, pp. 638–647 (2019). https://doi.org/10.1109/WACV.2019.00073
Lee, N., Hong, S., Kim, H.: Single-Trace Attack Using One-Shot Learning With Siamese Network in Non-Profiled Setting. IEEE Access 10, 60778–60789 (2022). https://doi.org/10.1109/ACCESS.2022.3180742
Wu, Y., et al.: A novel Siamese network object tracking algorithm based on tensor space mapping and memory-learning mechanism. J. Vis. Commun. Image. Represent. 91, 103742 (2023)
Heidari, M., Fouladi-Ghaleh, K.: Using Siamese networks with transfer learning for face recognition on small-samples datasets. 2020 International Conference on Machine Vision and Image Processing (MVIP). IEEE, pp. 1–4 (2020). https://doi.org/10.1109/MVIP49855.2020.9116915
Deng, J., et al.: Imagenet: A large-scale hierarchical image database. 2009 IEEE conference on computer vision and pattern recognition. IEEE, pp. 248–255 (2009). https://doi.org/10.1109/CVPR.2009.5206848
Amin, A.H.M., Khan, A.I.: One-shot classification of 2‑D leaf shapes using distributed hierarchical graph neuron (DHGN) scheme with k‑NN classifier. Procedia Comput Sci 24, 84–96 (2013)
Vilcek, A., et al.: Transformer-Based Deep Siamese Network for At-Scale Product Matching and One-Shot Hierarchy Classification (2018)
Song, C., Ji, S.: Face Recognition Method Based on Siamese Networks Under Non-Restricted Conditions. IEEE Access 10, 40432–40444 (2022). https://doi.org/10.1109/ACCESS.2022.3167143
Melekhov, I., Kannala, J., Rahtu, E.: Siamese network features for image matching. 2016 23rd international conference on pattern recognition (ICPR). IEEE, pp. 378–383 (2016). https://doi.org/10.1109/ICPR.2016.7899663
Schroff, F., Kalenichenko, D., Facenet, P.J.: A unified embedding for face recognition and clustering. Proceedings of the IEEE conference on computer vision and pattern recognition., pp. 815–823 (2015)
Daudt, R.C., Le Saux, B., Boulch, A.: Fully convolutional siamese networks for change detection. 2018 25th IEEE International Conference on Image Processing (ICIP). IEEE, pp. 4063–4067 (2018). https://doi.org/10.1109/ICIP.2018.8451652
Wu, Y., et al.: Siamese capsule networks with global and local features for text classification. Neurocomputing 390, 88–98 (2020)
Wang, C., Tzanetakis, G.: Singing style investigation by residual siamese convolutional neural networks. 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, pp. 116–120 (2018). https://doi.org/10.1109/ICASSP.2018.8461660
He, A., et al.: A twofold siamese network for real-time object tracking. Proceedings of the IEEE conference on computer vision and pattern recognition., pp. 4834–4843 (2018)
Barz, B., Denzler, J.: Hierarchy-based image embeddings for semantic image retrieval. 2019 IEEE winter conference on applications of computer vision (WACV). IEEE, pp. 638–647 (2019). https://doi.org/10.1109/WACV.2019.00073
Memon, S.A., Khan, K.A., Naveed, H.: HECNet: a hierarchical approach to enzyme function classification using a Siamese Triplet Network. Bioinformatics 36(17), 4583–4589 (2020). https://doi.org/10.1093/bioinformatics/btaa536
Ge, W.: Deep metric learning with hierarchical triplet loss. Proceedings of the European conference on computer vision (ECCV)., pp. 269–285 (2018)
Haque, T.U., Saber, N.N., Shah, F.M.: Sentiment analysis on large scale Amazon product reviews. 2018 IEEE international conference on innovative research and development (ICIRD). IEEE, pp. 1–6 (2018). https://doi.org/10.1109/ICIRD.2018.8376299
Xiao, H., Rasul, K., Vollgraf, R.: Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms. (2017). arXiv preprint arXiv:1708.07747
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Adv. Neural Inf. Process. Syst. – (2012). https://doi.org/10.1145/3065386
He, K., et al.: Deep residual learning for image recognition. Proceedings of the IEEE conference on computer vision and pattern recognition., pp. 770–778 (2016)
Sak, H., Senior, A., Beaufays, F.: Long short-term memory based recurrent neural network architectures for large vocabulary speech recognition. (2014). arXiv preprint arXiv:1402.1128
Kingma, D.P., Ba, J.A.: A method for stochastic optimization. (2014). arXiv preprint arXiv:1412.6980
Mikolov, T., et al.: Efficient estimation of word representations in vector space. (2013). arXiv preprint arXiv:1301.3781
Maćkiewicz, A., Ratajczak, W.: Principal components analysis (PCA). Comput. Geosci. 19(3), 303–342 (1993)
Gan, Y., Yang, J., Lai, W.: Video object forgery detection algorithm based on VGG-11 convolutional neural network. 2019 International Conference on Intelligent Computing, Automation and Systems (ICICAS). IEEE, pp. 575–580 (2019). https://doi.org/10.1109/ICICAS48597.2019.00126
Mannor, S., Peleg, D., Rubinstein, R.: The cross entropy method for classification. Proceedings of the 22nd international conference on Machine learning, vol. 2005, pp. 561–568
Funding
This research was performed in the framework of the state task in the field of scientific activity of the Ministry of Science and Higher Education of the Russian Federation, project “Models, methods, and algorithms of artificial intelligence in the problems of economics for the analysis and style transfer of multidimensional datasets, time series forecasting, and recommendation systems design”, grant no. FSSW-2023-0004.
Author information
Authors and Affiliations
Corresponding author
Additional information
Translated from Prikladnaya Matematika i Informatika, No. 73, 2023, pp. 38–57.
This article is a translation of the original article published in Russian in the journal Prikladnaya Matematika i Informatika. The translation was done with the help of an artificial intelligence machine translation tool, and subsequently reviewed and revised by an expert with knowledge of the field. Springer Nature works continuously to further the development of tools for the production of journals, books and on the related technologies to support the authors.
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Ponamaryov, V., Kitov, V. & Kitov, V. Accounting for class hierarchy in object classification using Siamese neural networks. Comput Math Model (2024). https://doi.org/10.1007/s10598-024-09593-w
Accepted:
Published:
DOI: https://doi.org/10.1007/s10598-024-09593-w