Abstract
Convolutional neural networks (CNNs) can achieve remarkable performance in many computer vision tasks (e.g. classification, detection and segmentation of images). However, the lack of labelled data can significantly hinder their generalization capabilities and limit the scope of their applications. Synthetic data augmentation (DA) is commonly used to address this issue, but uniformly applying global transformations can result in suboptimal performance when certain changes are more relevant to specific classes. The success of DA can be improved by adopting class-specific data transformations. However, this leads to an exponential increase in the number of combinations of image transformations. Finding an optimal combination is challenging due to a large number of possible transformations (e.g. some augmentation libraries offering up to sixty default transformations) and the training times of CNNs required to evaluate each combination. Here, we present an evolutionary approach using a genetic algorithm (GA) to search for an optimal combination of class-specific transformations subject to a feasible time constraint. Our study demonstrates a GA finding augmentation strategies that are significantly superior to those chosen randomly. We discuss and highlight the benefits of using class-specific data augmentation, how our evolutionary approach can automate the search for optimal DA strategies, and how it can be improved.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Arlot, S., Celisse, A.: A survey of cross-validation procedures for model selection (2010)
Bäck, T., Schwefel, H.P.: An overview of evolutionary algorithms for parameter optimization. Evol. Comput. 1(1), 1–23 (1993)
Bharati, S., Podder, P., Mondal, M.R.H.: Hybrid deep learning for detecting lung diseases from x-ray images. Inform. Med. Unlocked 20, 100391 (2020)
Buslaev, A., Iglovikov, V.I., Khvedchenya, E., Parinov, A., Druzhinin, M., Kalinin, A.A.: Albumentations: fast and flexible image augmentations. Information 11(2) (2020). https://doi.org/10.3390/info11020125, https://www.mdpi.com/2078-2489/11/2/125
Cubuk, E.D., Zoph, B., Mané, D., Vasudevan, V., Le, Q.V.: Autoaugment: learning augmentation policies from data. CoRR abs/1805.09501 (2018). http://arxiv.org/abs/1805.09501
Dana, H., Ballard, C.M.B.: Computer Vision. Prentice-Hall, Hoboken (1982)
Eastwood, M., et al.: Malignant mesothelioma subtyping of tissue images via sampling driven multiple instance prediction. In: Michalowski, M., Abidi, S.S.R., Abidi, S. (eds.) Artificial Intelligence in Medicine. AIME 2022. LNCS, vol. 13263, pp. 263–272. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-09342-5_25
Eiben, A.E., Smith, J.E.: Introduction to Evolutionary Computing. Springer, Berlin, Heidelberg (2015). https://doi.org/10.1007/978-3-662-43631-8_2
Erhan, D., Szegedy, C., Toshev, A., Anguelov, D.: Scalable object detection using deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2147–2154 (2014)
Frid-Adar, M., Diamant, I., Klang, E., Amitai, M., Goldberger, J., Greenspan, H.: Gan-based synthetic medical image augmentation for increased CNN performance in liver lesion classification. Neurocomputing 321, 321–331 (2018). https://doi.org/10.1016/j.neucom.2018.09.013, https://www.sciencedirect.com/science/article/pii/S0925231218310749
Ge, Y., Zhang, R., Wu, L., Wang, X., Tang, X., Luo, P.: A versatile benchmark for detection, pose estimation, segmentation and re-identification of clothing images. In: CVPR (2019)
Goodfellow, I.J., Bengio, Y., Courville, A.: Deep Learning. MIT Press, Cambridge, MA, USA (2016). http://www.deeplearningbook.org
Hauberg, S., Freifeld, O., Larsen, A.B.L., III, J.W.F., Hansen, L.K.: Dreaming more data: class-dependent distributions over diffeomorphisms for learned data augmentation. CoRR abs/1510.02795 (2015). http://arxiv.org/abs/1510.02795
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. CoRR abs/1512.03385 (2015). http://arxiv.org/abs/1512.03385
Hu, F., Xia, G.S., Hu, J., Zhang, L.: Transferring deep convolutional neural networks for the scene classification of high-resolution remote sensing imagery. Remote Sens. 7(11), 14680–14707 (2015)
Khan, S., Javed, M.H., Ahmed, E., Shah, S.A.A., Ali, S.U.: Facial recognition using convolutional neural networks and implementation on smart glasses. In: 2019 International Conference on Information Science and Communication Technology (ICISCT), pp. 1–6 (2019). https://doi.org/10.1109/CISCT.2019.8777442
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization (2014). https://doi.org/10.48550/ARXIV.1412.6980, https://arxiv.org/abs/1412.6980
Kirkpatrick, S., Gelatt, C.D., Vecchi, J.M.P.: Optimization by simulated annealing. Science 220(4598), 671–680 (1983)
Koidl, K.: Loss functions in classification tasks. School of Computer Science and Statistic Trinity College, Dublin (2013)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Commun. ACM 60(6), 84–90 (2017)
Nivin, T.W., Scott, G.J., Hurt, J.A., Chastain, R.L., Davis, C.H.: Exploring the effects of class-specific augmentation and class coalescence on deep neural network performance using a novel road feature dataset. In: 2018 IEEE Applied Imagery Pattern Recognition Workshop (AIPR), pp. 1–7 (2018). https://doi.org/10.1109/AIPR.2018.8707406
Paszke, A., et al.: Pytorch: an imperative style, high-performance deep learning library. CoRR abs/1912.01703 (2019). http://arxiv.org/abs/1912.01703
Pereira, S., Correia, J., Machado, P.: Evolving data augmentation strategies. In: Jiménez Laredo, J.L., Hidalgo, J.I., Babaagba, K.O. (eds.) EvoApplications 2022. LNCS, vol. 13224, pp. 337–351. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-02462-7_22
Rebuffi, S., Gowal, S., Calian, D.A., Stimberg, F., Wiles, O., Mann, T.A.: Data augmentation can improve robustness. CoRR abs/2111.05328 (2021). https://arxiv.org/abs/2111.05328
S, A.K., Pal, A., Mopuri, K.R., Krishna Gorthi, R.: Adv-cut paste: semantic adversarial class specific data augmentation technique for object detection. In: 2022 26th International Conference on Pattern Recognition (ICPR), pp. 3632–3638 (2022). https://doi.org/10.1109/ICPR56361.2022.9956409
Shorten, C., Khoshgoftaar, T.: A survey on image data augmentation for deep learning. J. Big Data 6(1), 1–48 (2019)
Sonka, M., Hlavac, V., Boyle, R.: Image processing, analysis, and machine vision. Cengage Learning (2014)
Terauchi, A., Mori, N.: Evolutionary approach for autoaugment using the thermodynamical genetic algorithm. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 9851–9858 (2021)
Ying, X.: An overview of overfitting and its solutions. J. Phys. Conf. Ser. 1168(2), 022022 (2019). https://doi.org/10.1088/1742-6596/1168/2/022022, https://dx.doi.org/10.1088/1742-6596/1168/2/022022
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Marc, S.T., Belavkin, R., Windridge, D., Gao, X. (2024). An Evolutionary Approach to Automated Class-Specific Data Augmentation for Image Classification. In: Moosaei, H., Hladík, M., Pardalos, P.M. (eds) Dynamics of Information Systems. DIS 2023. Lecture Notes in Computer Science, vol 14321. Springer, Cham. https://doi.org/10.1007/978-3-031-50320-7_12
Download citation
DOI: https://doi.org/10.1007/978-3-031-50320-7_12
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-50319-1
Online ISBN: 978-3-031-50320-7
eBook Packages: Computer ScienceComputer Science (R0)