Abstract
Label ambiguity in data is one of the serious challenges in Machine Learning. In such cases, the significance of each label matters. Label Distribution Learning (LDL) is a new way to deal with label ambiguity. In LDL, instances are defined through the degree to which it is represented by its labels or classes. In this paper, deep learning using autoencoders has been proposed for a computing this degree of labels. The autoencoder consists two parts i.e., encoder and decoder. The encoder compresses the input whereas the decoder decompresses it. The idea of compression is to learn relationship between patterns of data which remains unchanged. The idea of decompression is to recover the original input from the compressed input. Since autoencoders are semi-supervised we have appended a fully connected network for computing degree for each labels. Our results show that DLDL shows the least mean-square error among the contemporary methods.
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
Geng, X., Smith-Miles, K., Zhou, Z.-H.: Facial age estimation by learning from label distributions. In: Proceedings of 24th AAAI Conference Artificial Intelligence, Atlanta, GA, pp. 451–456 (2010)
Geng, X., Yin, C., Zhou, Z.-H.: Facial age estimation by learning from label distributions. IEEE Trans. Pattern Anal. Mach. Intell. 35(10), 2401–2412 (2013)
Geng, X.: Label distribution learning. IEEE Trans. Knowl. Data Eng. 28(7), 1734–1748 (2016)
Biswas, M., Kuppili, V., Edla, D.: ALDL: a novel method for label distribution learning. Sādhanā 44(3), 53 (2019)
Kuppili, V., Biswas, M., Reddy, D.: PLDL: a novel method for label distribution learning. Sādhanā 16, 1021–1027 (2019)
Biswas, M., et al.: State-of-the-art review on deep learning in medical imaging. Front. Biosci. (Landmark edition) 24, 392–426 (2019)
Saba, L., et al.: The present and future of deep learning in radiology. Eur. J. Radiol. 114, 14–24 (2019)
Hinton, G.E., Krizhevsky, A., Wang, S.D.: Transforming auto-encoders. In: Honkela, T., Duch, W., Girolami, M., Kaski, S. (eds.) ICANN 2011. LNCS, vol. 6791, pp. 44–51. Springer, Heidelberg (2011). https://doi.org/10.1007/978-3-642-21735-7_6
Eisen, M.B., Spellman, P.T., Brown, P.O., Botstein, D.: Cluster analysis and display of genome-wide expression patterns. Proc. Natl. Acad. Sci. 95(25), 14863–14868 (1998)
Lyons, M.J., Akamatsu, S., Kamachi, M., Gyoba, J., Budynek, J.: The Japanese female facial expression (JAFFE) database. In: Proceedings of Third International Conference on Automatic Face and Gesture Recognition, pp. 14–16 (1998)
Biswas, M., et al.: Symtosis: a liver ultrasound tissue characterization and risk stratification in optimized deep learning paradigm. Comput. Methods Prog. Biomed. 155, 165–177 (2018)
Huang, G.B., Zhu, Q.Y., Siew, C.K.: Extreme learning machine: theory and applications. Neurocomputing 70, 489–501 (2006)
Hou, P., Geng, X., Huo, Z. W., Lv, J.Q.: In: Thirty-First AAAI Conference on Artificial Intelligence (2017)
Taud, H., Mas, J.F.: Geomatic approaches for modeling land change scenarios, pp. 451–455 (2018)
Moré, J.J.: The Levenberg-Marquardt algorithm: implementation and theory. In: Watson, G.A. (ed.) Numerical Analysis. LNM, vol. 630, pp. 105–116. Springer, Heidelberg (1978). https://doi.org/10.1007/BFb0067700
Goudreau, M.W., Giles, C.L., Chakradhar, S.T., Chen, D.: First-order versus second-order single-layer recurrent neural networks. IEEE Trans. Neural Netw. 5, 511–513 (1994)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Biswas, M., Suri, J.S. (2022). Deep-learning Based Autoencoder Model for Label Distribution Learning. In: Mukhopadhyay, S., Sarkar, S., Dutta, P., Mandal, J.K., Roy, S. (eds) Computational Intelligence in Communications and Business Analytics. CICBA 2022. Communications in Computer and Information Science, vol 1579. Springer, Cham. https://doi.org/10.1007/978-3-031-10766-5_5
Download citation
DOI: https://doi.org/10.1007/978-3-031-10766-5_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-10765-8
Online ISBN: 978-3-031-10766-5
eBook Packages: Computer ScienceComputer Science (R0)