Abstract
As the size of the dataset used in deep learning tasks increases, the noisy label problem, which is a task of making deep learning robust to the incorrectly labeled data, has become an important task. In this paper, we propose a method of learning noisy label data using the label noise selection with test-time augmentation (TTA) cross-entropy and classifier learning with the NoiseMix method. In the label noise selection, we propose TTA cross-entropy by measuring the cross-entropy to predict the test-time augmented training data. In the classifier learning, we propose the NoiseMix method based on MixUp and BalancedMix methods by mixing the samples from the noisy and the clean label data. In experiments on the ISIC-18 public skin lesion diagnosis dataset, the proposed TTA cross-entropy outperformed the conventional cross-entropy and the TTA uncertainty in detecting label noise data in the label noise selection process. Moreover, the proposed NoiseMix not only outperformed the state-of-the-art methods in the classification performance but also showed the most robustness to the label noise in the classifier learning.
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
Codella, N.C.F., et al.: Skin lesion analysis toward melanoma detection: a challenge at the 2017 international symposium on biomedical imaging (ISBI), hosted by the international skin imaging collaboration (ISIC). In: 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018), pp. 168–172 (2018)
Codella, N.C.F., et al.: Skin lesion analysis toward melanoma detection: a challenge at the 2017 international symposium on biomedical imaging (ISBI), hosted by the international skin imaging collaboration (ISIC). CoRR arXiv:abs/1710.05006 (2017)
Codella, N.C.F., et al.: Skin lesion analysis toward melanoma detection 2018: a challenge hosted by the international skin imaging collaboration (ISIC). CoRR arXiv:abs/1902.03368 (2019)
Combalia, M., et al.: Bcn20000: dermoscopic lesions in the wild (2019)
Englesson, E., Azizpour, H.: Consistency regularization can improve robustness to label noise. CoRR arXiv:abs/2110.01242 (2021)
Galdran, A., Carneiro, G., González Ballester, M.A.: Balanced-mixup for highly imbalanced medical image classification. In: De Bruijne, M., et al. (eds.) MICCAI 2021. LNCS, vol. 12905, pp. 323–333. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-87240-3_31
Han, B., et al.: Co-teaching: robust training of deep neural networks with extremely noisy labels. In: Bengio, S., Wallach, H., Larochelle, H., Grauman, K., Cesa-Bianchi, N., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 31. Curran Associates, Inc. (2018)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2016
Hendrycks, D., Mu, N., Cubuk, E.D., Zoph, B., Gilmer, J., Lakshminarayanan, B.: AugMix: a simple data processing method to improve robustness and uncertainty. In: Proceedings of the International Conference on Learning Representations (ICLR) (2020)
Ju, L., et al.: Improving medical images classification with label noise using dual-uncertainty estimation. IEEE Trans. Med. Imaging 41(6), 1533–1546 (2022)
Karimi, D., Dou, H., Warfield, S.K., Gholipour, A.: Deep learning with noisy labels: exploring techniques and remedies in medical image analysis. Med. Image Anal. 65, 101759 (2020)
Li, J., Socher, R., Hoi, S.C.: Dividemix: learning with noisy labels as semi-supervised learning. In: International Conference on Learning Representations (2020)
Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A.A.: Inception-v4, inception-resnet and the impact of residual connections on learning. In: Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, pp. 4278–4284 (2017)
Tschandl, P., Rosendahl, C., Kittler, H.: The ham10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions. Sci. Data 5(1), 180161 (2018)
Xue, Y., Whitecross, K., Mirzasoleiman, B.: Investigating why contrastive learning benefits robustness against label noise. CoRR arXiv:abs/2201.12498 (2022)
Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: Mixup: beyond empirical risk minimization. In: International Conference on Learning Representations (2018)
Acknowledgments
This work was supported by the National Research Foundation of Korea(NRF) grant funded by the Korea government(MSIT) (No. 2020 R1A2C1102140), and the Korea Medical Device Development Fund grant funded by the Korea government (the Ministry of Science and ICT, the Ministry of Trade, Industry and Energy, the Ministry of Health & Welfare, the Ministry of Food and Drug Safety) (Project Number: 9991007550, KMDF_PR_20200901_0269).
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
Lee, H., Lee, H., Hong, H., Kim, J. (2022). Noisy Label Classification Using Label Noise Selection with Test-Time Augmentation Cross-Entropy and NoiseMix Learning. In: Nguyen, H.V., Huang, S.X., Xue, Y. (eds) Data Augmentation, Labelling, and Imperfections. DALI 2022. Lecture Notes in Computer Science, vol 13567. Springer, Cham. https://doi.org/10.1007/978-3-031-17027-0_8
Download citation
DOI: https://doi.org/10.1007/978-3-031-17027-0_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-17026-3
Online ISBN: 978-3-031-17027-0
eBook Packages: Computer ScienceComputer Science (R0)
