Abstract
We study anomaly detection for the case when the normal class consists of more than one object category. This is an obvious generalization of the standard one-class anomaly detection problem. However, we show that jointly using multiple one-class anomaly detectors to solve this problem yields poorer results as compared to training a single one-class anomaly detector on all normal object categories together. We further develop a new anomaly detector called DeepMAD that learns compact distinguishing features by exploiting the multiple normal objects categories. This algorithm achieves higher AUC values for different datasets compared to two top performing one-class algorithms that either are trained on each normal object category or jointly trained on all normal object categories combined. In addition to theoretical results we present empirical results using the CIFAR-10, fMNIST, CIFAR-100, and a new dataset we developed called RECYCLE.
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
Abati, D., Porrello, A., Calderara, S., Cucchiara, R.: And: autoregressive novelty detectors. In: Proceedings of the CVPR (2019)
Ackay, A., Atapour-Abarghouei, A., Breckopn, T.P.: Ganomaly: semi-supervised anomaly detection via adversarial training. In: Proceedings of the ACCV, pp. 622–637 (2018)
Ahmed, F., Courville, A.: Detecting semantic anomalies. In: Proceedings of the AAAI, vol. 34, pp. 3154–3162 (2020)
Bergman, L., Hoshen, Y.: Classification-based anomaly detection for general data. In: Proceedings of the ICLR (2020)
Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: Proceedings of the ICML (2020)
Clemen, R.T., Winkler, R.L.: Combining probability distributions from experts in risk analysis. Risk Anal. 19(2), 187–203 (1999)
Dempster, A.P.: Upper and lower probabilities induced by a multivalued mapping. Ann. Math. Stat. 38(2), 325–339 (1967)
DeVries, T., Taylor, G.W.: Learning confidence for out-of-distribution detection in neural networks (2018)
Ghafoori, Z., Leckie, C.: Deep multi-sphere support vector data description. In: SIAM SDM (2020)
Golan, I., El-Yaniv, R.: Deep anomaly detection using geometric transformations. In: Proceedings of the NeurIPS (2018)
Goyal, S., Raghunathan, A., Simhadri, M., Jain, P.: DROCC: deep robust one-class classification. In: Proceedings of the ICML (2020)
Hendrycks, D., Gimpel, K.: A baseline for detecting misclassified and out-of-distribution examples in neural networks. In: Proceedings of the ICLR (2017)
Hendrycks, D., Mazeika, M., Dietterich, T.: Deep anomaly detection with outlier exposure. In: Proceedings of the ICLR (2019)
Hendrycks, D., Mazeika, M., Kadavath, S., Song, D.: Using self-supervised learning can improve model robustness and uncertainity. In: Proceedings of the NeurIPS (2019)
Lakshminarayanan, B., Pritzel, A., Blundell, C.: Simple and scalable predictive uncertainity estimation using deep ensembles. In: 31st Conference on Neural Information Processing Systems (2017)
Lee, K., Lee, H., Lee, K., Shin, J.: Training confidence-calibrated classifiers for detecting out-of-distribution samples (2018)
Li, D., Chen, D., Goh, J., Ng, S.K.: Anomaly detection with generative adversarial networks for multivariate time series. In: 7th International Workshop on Big Data, Streams and Heterogeneous Source Mining: Algorithms, Systems, Programming Models and Applications (ACM KDD), August 2018
Liang, S., Li, Y., Srikant, R.: Enhancing the reliability of out-of-distribution image detection in neural networks. In: Proceedings of the International Conference on Learned Representations (ICLR 2018), February 2018
Masana, M., Ruiz, I., Serrat, J., van de Weijer, J., Lopez, A.M.: Metric learning for novelty and anomaly detection. In: British Machine Vision Conference (2018)
Nguyen, D.T., Lou, Z., Klar, M., Brox, T.: Anomaly detection with multiple-hypothesis predictions. In: Proceedings of the ICML (2019)
Perera, P., Nallapati, R., Xiang, B.: Ocgan: one-class novelty detection using gans with constrained latent representations. In: Proceedings of the CVPR (2019)
Perera, P., Patel, V.M.: Deep transfer learning for multiple class novelty detection. In: Proceedings of the CVPR (2019)
Pidhorskyi, S., Almohsen, R., Adjeroh, D.A., Doretto, G.: Generative probabilistic novelty detection with adversarial autoencodres. In: Proceedings of the NeurIPS (2018)
Pimentel, M.A.F., Clifton, D.A., Clifton, L., Tarassenko, L.: A review of novelty detection. Signal Processing, pp. 215–249 (2014)
Ren, J., et al.: Likelihood ratios for out-of-distribution detection. In: 33rd Conference on Neural Information Processing Systems (2019)
Ruff, L., et al.: Deep one-class classification. In: Proceedings 35th International Conference on Machine learning (ICML). Stockholm, Sweeden (2018)
Ruff, L., et al.: Deep semi-supervised anomaly detection. In: Proceedings of the ICLR (2020)
Ruff, L., et al.: A unifying review of deep and shallow anomaly detection, September 2020. arXiv:2009.11732v2
Sabokrou, M., Khalooei, M., Fathy, M., Adeli, E.: Adversarially learned one-class classifier for novelty detection. In: Proceedings of the CVPR, pp. 3379–3388 (2018)
Schlegl, T., Seebock, P., Waldstein, S.M., Schmidt-Erfurth, U., Langs, G.: Unsupervised anomaly detection with generative adversarial networks to guide marker discovery. In: International Conference on Information Processing in Medical Imaging, pp. 146–157 (2017)
Shafer, G.: Mathematical Theory of Evidence. Princeton University Press, Princeton (1976)
Sohn, K., Li, C.L., Yoon, J., Jin, M., Pfister, T.: Learning and evaluating representations for deep one-class classification. In: Proceedings of the ICLR (2021)
Song, H., Jiang, Z., Men, A., Yang, B.: A hybrid semi-supervised anomaly detection model for high-dimensional data. Computational Intelligence and Neuroscience (2017)
Tack, J., Mo, S., Jeong, J., Shin, J.: CSI: novelty detection via contrastive learning on distributionally shifted instances. In: Proceedings of the NeurIPS (2020)
Vyas, A., Jammalamadaka, N., Zhu, X., Das, D., Kaul, B., Wilke, T.L.: Out-of-distribution detection using an ensemble of self-supervised leave-out classifiers. In: Proceedings of the ECCV, pp. 550–564 (2018)
Zhang, H., Li, A., Guo, J., Guo, Y.: Hybrid models for open set recognition (2020)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Singh, S., Luo, M., Li, Y. (2023). Multi-Class Anomaly Detection. In: Tanveer, M., Agarwal, S., Ozawa, S., Ekbal, A., Jatowt, A. (eds) Neural Information Processing. ICONIP 2022. Lecture Notes in Computer Science, vol 13625. Springer, Cham. https://doi.org/10.1007/978-3-031-30111-7_31
Download citation
DOI: https://doi.org/10.1007/978-3-031-30111-7_31
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-30110-0
Online ISBN: 978-3-031-30111-7
eBook Packages: Computer ScienceComputer Science (R0)