Abstract
In the context of imbalanced classification, deep neural networks suffer from the lack of samples provided by low represented classes. They can’t train enough their weights with a statistically reliable set. All solutions in the state of the art that could offer better performance for those classes, sacrifice in return a huge part of their precision on bigger classes. In this paper, we propose a solution to this problem by introducing a system cascade concept that could integrate deep neural network. This system is designed to keep as mush as possible the original network performance while it reinforces the classification of the minor classes by the addition of stages with more specialised systems. This cascade offers the possibility to integrate few-shot learning or incremental architecture following the deep neural network without major restrictions on system internal architecture. Our method keeps intact or slightly improves the performances of a deep neural network (used as first stage) in conventional cases and improves performances in strongly imbalanced cases by around +8% accuracy.
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
Similar content being viewed by others
References
Aaron, B., Tamir, D.E., Rishe, N.D., Kandel, A.: Dynamic incremental k-means clustering. In: 2014 International Conference on Computational Science and Computational Intelligence, vol. 1, pp. 308–313. IEEE (2014)
Bakkali, S., Ming, Z., Coustaty, M., Rusinol, M.: Visual and textual deep feature fusion for document image classification. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 562–563 (2020)
Bouguelia, M.R., Belaïd, Y., Belaïd, A.: A stream-based semi-supervised active learning approach for document classification. In: 2013 12th International Conference on Document Analysis and Recognition, pp. 611–615. IEEE (2013)
Cho, K., et al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078 (2014)
d’Andecy, V.P., Joseph, A., Ogier, J.M.: IndUS: incremental document understanding system focus on document classification. In: 2018 13th IAPR International Workshop on Document Analysis Systems (DAS), pp. 239–244. IEEE (2018)
Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)
Fei-Fei, L., Fergus, R., Perona, P.: One-shot learning of object categories. IEEE Trans. Pattern Anal. Mach. Intell. 28(4), 594–611 (2006)
Górriz, M., Antony, J., McGuinness, K., Giró-i Nieto, X., O’Connor, N.E.: Assessing knee OA severity with CNN attention-based end-to-end architectures. arXiv preprint arXiv:1908.08856 (2019)
Harley, A.W., Ufkes, A., Derpanis, K.G.: Evaluation of deep convolutional nets for document image classification and retrieval. In: 2015 13th International Conference on Document Analysis and Recognition (ICDAR), pp. 991–995. IEEE (2015)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700–4708 (2017)
Joulin, A., Grave, E., Bojanowski, P., Douze, M., Jégou, H., Mikolov, T.: Fasttext. zip: Compressing text classification models. arXiv preprint arXiv:1612.03651 (2016)
Kim, Y.: Convolutional neural networks for sentence classification. arXiv preprint arXiv:1408.5882 (2014)
Koch, G., Zemel, R., Salakhutdinov, R.: Siamese neural networks for one-shot image recognition. In: ICML Deep Learning Workshop, Lille, vol. 2 (2015)
Kochurov, M., Garipov, T., Podoprikhin, D., Molchanov, D., Ashukha, A., Vetrov, D.: Bayesian incremental learning for deep neural networks. arXiv preprint arXiv:1802.07329 (2018)
Lai, S., Xu, L., Liu, K., Zhao, J.: Recurrent convolutional neural networks for text classification. In: Twenty-Ninth AAAI Conference on Artificial Intelligence (2015)
Lake, B.M., Salakhutdinov, R., Tenenbaum, J.B.: Human-level concept learning through probabilistic program induction. Science 350(6266), 1332–1338 (2015)
Laskov, P., Gehl, C., Krüger, S., Müller, K.R.: Incremental support vector learning: analysis, implementation and applications. J. Mach. Learn. Res. 7, 1909–1936 (2006)
Martin, L., et al.: CamemBERT: a tasty French language model. arXiv preprint arXiv:1911.03894 (2019)
Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781 (2013)
Palm, R.B., Winther, O., Laws, F.: CloudScan-a configuration-free invoice analysis system using recurrent neural networks. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol. 1, pp. 406–413. IEEE (2017)
Rosenfeld, A., Tsotsos, J.K.: Incremental learning through deep adaptation. IEEE Trans. Pattern Anal. Machine Intell. 42, 651–663 (2018)
Santoro, A., Bartunov, S., Botvinick, M., Wierstra, D., Lillicrap, T.: One-shot learning with memory-augmented neural networks. arXiv preprint arXiv:1605.06065 (2016)
Sarwar, S.S., Ankit, A., Roy, K.: Incremental learning in deep convolutional neural networks using partial network sharing. IEEE Access 8, 4615–4628 (2019)
Schuster, D., et al.: Intellix-end-user trained information extraction for document archiving. In: 2013 12th International Conference on Document Analysis and Recognition, pp. 101–105. IEEE (2013)
Schuster, M., Paliwal, K.K.: Bidirectional recurrent neural networks. IEEE Trans. Signal Process. 45(11), 2673–2681 (1997)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
Snell, J., Swersky, K., Zemel, R.S.: Prototypical networks for few-shot learning. arXiv preprint arXiv:1703.05175 (2017)
Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A.A.: Inception-v4, inception-ResNet and the impact of residual connections on learning. In: Thirty-First AAAI Conference on Artificial Intelligence (2017)
Voerman, J., Joseph, A., Coustaty, M., Poulain d’Andecy, V., Ogier, J.-M.: Evaluation of neural network classification systems on document stream. In: Bai, X., Karatzas, D., Lopresti, D. (eds.) DAS 2020. LNCS, vol. 12116, pp. 262–276. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-57058-3_19
Wang, Y., Yao, Q., Kwok, J.T., Ni, L.M.: Generalizing from a few examples: a survey on few-shot learning. ACM Comput. Surv. (CSUR) 53(3), 1–34 (2020)
Xian, Y., Schiele, B., Akata, Z.: Zero-shot learning-the good, the bad and the ugly. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4582–4591 (2017)
Zhang, X., Zhao, J., LeCun, Y.: Character-level convolutional networks for text classification. In: Advances in Neural Information Processing Systems, pp. 649–657 (2015)
Zoph, B., Vasudevan, V., Shlens, J., Le, Q.V.: Learning transferable architectures for scalable image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8697–8710 (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Voerman, J., Mahamoud, I.S., Joseph, A., Coustaty, M., d’Andecy, V.P., Ogier, JM. (2021). Toward an Incremental Classification Process of Document Stream Using a Cascade of Systems. In: Barney Smith, E.H., Pal, U. (eds) Document Analysis and Recognition – ICDAR 2021 Workshops. ICDAR 2021. Lecture Notes in Computer Science(), vol 12917. Springer, Cham. https://doi.org/10.1007/978-3-030-86159-9_16
Download citation
DOI: https://doi.org/10.1007/978-3-030-86159-9_16
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-86158-2
Online ISBN: 978-3-030-86159-9
eBook Packages: Computer ScienceComputer Science (R0)
