Abstract
Deep learning based approaches have shown promising results for anomaly detection. One of them is the one-class classification, a typical method treated as an unsupervised learning model. In this problem, a number of unlabeled samples are given. The model will learn a description of the unlabeled samples. The description is then used to detect an unusual sample and treat it as an anomaly object. It, however, should be better to learn an anomaly detector if we can have some labeled samples which include both normal and anomalous, to leverage the description of unlabeled samples. Learning with these labeled samples for anomaly detection is also known as the semi-supervised method. In this paper, we present an improvement of the deep SAD, a semi-supervised model, for anomaly detection in industrial systems. We propose to use synthetic anomalies which can be generated using noises. Two noise models are used, including the confetti and polygon noises, to augment the anomalies for training the model. Experiments will be conducted for the standard dataset MVTec-AD to show that our model outperforms related baseline models, especially with a small dataset available.
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
Reference
Akcay, S., Atapour-Abarghouei, A., Breckon, T. P.: GANomaly: semi-supervised anomaly detection via adversarial training. In: ACCV, pp. 622–637 (2018)
Bergman, L., Hoshen, Y.: Classification-based anomaly detection for general data. In: ICLR (2020)
Bergmann, P., Batzner, K., Fauser, M., Sattlegger, D., Steger, C.: The MVTec anomaly detection dataset: a comprehensive real-world dataset for unsupervised anomaly detection. Int. J. Comput. Vis. 129(4), 1038–1059 (2021). https://doi.org/10.1007/s11263-020-01400-4
Chalapathy, R., Chawla, S.: Deep learning for anomaly detection: a survey. arXiv:1901.03407 (2019)
Golan, I., El-Yaniv, R.: Deep anomaly detection using geometric transformations. In: NeurIPS 31 (2018)
Huang, C., Cao, J., Ye, F., Li, M., Zhang, Y., Lu, C.: Inverse-transform autoencoder for anomaly detection. arXiv preprint arXiv:1911.10676 (2019)
Kumagai, A., Iwata, T., Fujiwara, Y.: Semi-supervised anomaly detection on attributed graphs. In: International Joint Conference on Neural Networks (IJCNN), pp. 1–8 (2021)
Kim, J.S., Scott, C.D.: Robust kernel density estimation. J. Mach. Learn. Res. 13, 2529–2565 (2012)
Liznerski, P., Ruff, L., Vandermeulen R.A., Franks, B.J., Kloft, M., Müller, K.-R.: Explainable deep one-class classification. In: ICLR (2021)
Liu, F.T., Ting, K.M., Zhou, Z.-H.: Isolation forest. In: ICDM, pp. 413–422 (2008)
Liu, W., et al.: Towards visually explaining variational autoencoders. In: CVPR, pp. 8642–8651 (2020)
Lu, Y., Xu, P.: Anomaly detection for skin disease images using variational autoencoder. arXiv preprint arXiv:1807.01349 (2018)
Minhas, M., Zelek, J.: Semi-supervised anomaly detection using autoencoders. J. Comput. Vis. Imaging Syst. 5(1), 3 (2020)
Moya, M.M., Koch, M.W., Hostetler, L.D.: One-class classifier networks for target recognition applications. In: Proceedings World Congress on Neural Networks, pp. 797–801 (1993)
Perera, P., Nallapati, R., Xiang, B.: OCGAN: one-class novelty detection using GANs with constrained latent representations. In: CVPR, pp. 2898–2906 (2019)
Ruff, L., Vandermeulen, R., et al.: Deep one-class classification. In: ICML, vol. 80, pp. 4393–4402 (2018)
Ruff, L., et al.: Deep semi-supervised anomaly detection. In: ICLR (2020)
Sabokrou, M., Khalooei, M., Fathy, M., Adeli, E.: Adversarially learned one-class classifier for novelty detection. In: CVPR, pp. 3379–3388 (2018)
Schölkopf, B., Platt, J.C., Shawe-Taylor, J., Smola, A.J., Williamson, R.C.: Estimating the support of a high-dimensional distribution. Neural Comput. 13(7), 1443–1471 (2001)
Spahr, A., Bozorgtabar, B., Thiran, J-P.: Self-taught semi-supervised anomaly detection on upper limb x-rays. CoRR abs/2102.09895 (2021)
Tax, D.M., Duin, R.P.: Support vector data description. Mach. Learn. 54, 45–66 (2004)
Vandermeulen, R. A., Scott, C.: Consistency of robust kernel density estimators. In COLT, pp. 568–591 (2013)
Wang, T., et al.: Generative neural networks for anomaly detection in crowded scenes. IEEE Trans. Inf. Forensics Secur. 14(5), 1390–1399 (2019)
Zhu, C., Sundaram, G., Snoeyink, J., Mitchelld, J.S.B.: Generating random polygons with given vertices. Comput. Geom. 6(5), 277–290 (1996)
Acknowledgments
This work is funded by Saigon University, Ho Chi Minh City, Vietnam under the grant number [CS2021-13].
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Anh, N.T.H., Loan, D.N.N., Trang, L.H. (2021). One-Class Classification with Noise-Based Data Augmentation for Industrial Anomaly Detection. In: Dang, T.K., Küng, J., Chung, T.M., Takizawa, M. (eds) Future Data and Security Engineering. Big Data, Security and Privacy, Smart City and Industry 4.0 Applications. FDSE 2021. Communications in Computer and Information Science, vol 1500. Springer, Singapore. https://doi.org/10.1007/978-981-16-8062-5_13
Download citation
DOI: https://doi.org/10.1007/978-981-16-8062-5_13
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-8061-8
Online ISBN: 978-981-16-8062-5
eBook Packages: Computer ScienceComputer Science (R0)