Abstract
Computer Vision (CV) has been employed in several different industries, with remarkable success in image classification applications, such as medicine, production quality control, transportation systems, etc. CV models rely on excessive images to train prospective models. Usually, the process of acquiring images is expensive and time-consuming. In this study, we propose a method that consists of multiple steps to increase image classification accuracy with a small amount of data. In the initial step, we set up multiple datasets from an existing dataset. Because an image carries pixel values between 0 and 255, we divided the images into pixel intervals depending on dataset type. If the dataset is grayscale, the pixel interval is divided into two parts, whereas it is divided into five intervals when the dataset consists of RGB images. In the next step, we trained the model using the original dataset and each created datasets separately. In the training process, each image illustrates a non-identical prediction space where we propose a top-three prediction probability ensemble method. Top-three predictions of newly generated images are ensemble to the corresponding probabilities of the original image. Results demonstrate that learning patterns from each pixel interval and ensemble the top three prediction vastly improves the performance and accuracy and the method can be applied to any model.
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
Gaikwad, D.P., Thool, R.C.: Intrusion detection system using bagging ensemble method of machine learning. In: Proceedings – 1st International Conference on Computing, Communication, Control and Automation, ICCUBEA 2015, Jul 2015, pp. 291–295. https://doi.org/10.1109/ICCUBEA.2015.61
Tolstikhin, I., et al.: MLP-Mixer: an all-MLP architecture for vision, May 2021 [Online]. Available: http://arxiv.org/abs/2105.01601
Chollet, F.: Xception: deep learning with depthwise separable convolutions, Oct 2016 [Online]. Available: http://arxiv.org/abs/1610.02357
Krogh, A.: Neural network ensembles, cross validation, and active learning
Liu, N., Li, X., Qi, E., Xu, M., Li, L., Gao, B.: A novel ensemble learning paradigm for medical diagnosis with imbalanced data. IEEE Access 8, 171263–171280 (2020). https://doi.org/10.1109/ACCESS.2020.3014362
Chen, Y., Wang, Y., Gu, Y., He, X., Ghamisi, P., Jia, X.: Deep .learning ensemble for hyperspectral image classification. IEEE J. Sel. Top. Appl. Earth Observ. Remote Sens. 12(6), 1882–1897 (2019). https://doi.org/10.1109/JSTARS.2019.2915259
Soares, R.G.F., Chen, H., Yao, X.: A cluster-based semisupervised ensemble for multiclass classification. IEEE Trans. Emerg. Top. Comput. Intell. 1(6), 408–420 (2017). https://doi.org/10.1109/TETCI.2017.2743219
Nguyen, N.T., Sobecki, J.: Using consensus methods to construct adaptive interfaces in multimodal web-based systems. J. Univ. Access Inf. Soc. 2(4), 342–358 (2003)
Nguyen, N.T.: Conflicts of ontologies – classification and consensus-based methods for resolving. In: Gabrys, B., Howlett, R.J., Jain, L.C. (eds.) KES 2006. LNCS (LNAI), vol. 4252, pp. 267–274. Springer, Heidelberg (2006). https://doi.org/10.1007/11893004_34
Pietranik, M., Nguyen, N.T.: A multi-atrribute based framework for ontology aligning. Neurocomputing 146, 276–290 (2014)
Anorboev, A., Musaev, J.: An image pixel interval power (IPIP) method using deep learning classification models. Accepted to the proceeding of ACIIDS 2022 Conference
Acknowledgements
This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (No.2022R1F1A1074641).
Author information
Authors and Affiliations
Corresponding authors
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
Anorboev, A., Musaev, J., Hong, J., Nguyen, N.T., Hwang, D. (2022). SSTop3: Sole-Top-Three and Sum-Top-Three Class Prediction Ensemble Method Using Deep Learning Classification Models. In: Bădică, C., Treur, J., Benslimane, D., Hnatkowska, B., Krótkiewicz, M. (eds) Advances in Computational Collective Intelligence. ICCCI 2022. Communications in Computer and Information Science, vol 1653. Springer, Cham. https://doi.org/10.1007/978-3-031-16210-7_15
Download citation
DOI: https://doi.org/10.1007/978-3-031-16210-7_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-16209-1
Online ISBN: 978-3-031-16210-7
eBook Packages: Computer ScienceComputer Science (R0)