Skip to main content
SpringerLink
Log in

Mixture of experts with convolutional and variational autoencoders for anomaly detection

  • Published:
Applied Intelligence Aims and scope Submit manuscript

Abstract

This study focused on the problem of anomaly detection (AD) by means of mixture-of-experts network. Most of the existing AD methods solely based on the reconstruction errors or latent representation using a single low-dimensional manifold are often not ideal for the image objects with complex background. However, modeling the data as a mixture of low-dimensional nonlinear manifolds is natural and promising for the classification of anomalies. In this study to realize the promise of multi-manifold latent information for AD, we propose a mixture of experts ensemble with two convolutional variational autoencoders (CVAEs) and convolution network (MEx-CVAEC) which explicitly learns manifold relationships of data that make use of multiple encoded detections. Additionally, we integrate a linear-based CAE as a gating network which optimizes the expert structures for efficient data characterization based on the manifold of the latent space. In the expert structure the data is re-encoded after each decoder to enhance the latent detection performance and the VAE is used as a core element in the encoder-decoder-encode (EDE) pipeline. To the best of our knowledge, this is the first study suggesting a mixture of CVAEs-based models for AD. The performance of the MEx-CVAE with EDE pipeline which we names as (MEx-CVAEC) compared over two basic MEx-CVAE model with ED pipeline based on logistic regression (MEx-L) and based on CAE (MEx-C) structures. In addition, the performance of the proposed model on three different datasets show the highest average AUC value than that of the state-of-the-art for image anomalies detection task.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

References

  1. Calderara S, Heinemann U, Prati A, Cucchiara R, Tishby N (2011) Detectinganomalies in people’s trajectories using spectral graph analysis. Comput Vision Image Understand 115(8):1099–1111

    Article  Google Scholar 

  2. Hasan M, Choi J, Neumann J, Roy-Chowdhury AK, Davis LS (2016) Learning temporal regularity in video sequences. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 733–742

  3. Kumar A (2008) Computer-vision-based fabric defect detection: a survey. IEEE Trans Ind Electron 55(1):348–363

    Article  Google Scholar 

  4. Rashid MM, Amar M, Gondal I, Kamruzzaman J (2016) A data mining ap-proach for machine fault diagnosis based on associated frequency patterns. Appl Intell 45(3):638–651

    Article  Google Scholar 

  5. Kim J, Kim H-J, Kim H (2019) Fraud detection for job placement using hi-erarchical clusters-based deep neural networks. Appl Intell 49(8):2842–2861

    Article  Google Scholar 

  6. Kavitha MS, Kurita T, Park S-Y, Chien S-I, Bae J-S, Ahn B-C (2017) Deep vector-based convolutional neural network approach for automatic recognition of colonies of induced pluripotent stem cells. PLoS One 12(12):e0189974

    Article  Google Scholar 

  7. Wang X, Du Y, Lin S, Cui P, Shen Y, Yang Y (2020) Advae: A self-adversarial variational autoencoder with gaussian anomaly prior knowledgefor anomaly detection. Knowl-Based Syst 190:105187

    Article  Google Scholar 

  8. Li N, Chang F (2019) Video anomaly detection and localization via multivariategaussian fully convolution adversarial autoencoder. Neurocomputing 369:92–105

    Article  Google Scholar 

  9. Dufrenois F (2014) A one-class kernel fisher criterion for outlier detection. IEEE Trans Neural Netw Learn Syst 26(5):982– 994

    Article  MathSciNet  Google Scholar 

  10. Kavitha MS, Lee C -H, Shibudas K, kurita T (2020) B-C Ahn Deep learning enables automated localization of the metastatic lymph node for thyroid cancer on 131I post-ablation whole-body planar scans. Scientif Rep 10(7738)

  11. Loka NRBS, Kavitha MS, Kurita T (2019) Hilbert vector convolutional neural network: 2D neural network on 1D data. In: International conference on artificial neural networks. Springer, New York, pp 458–470

  12. Schlegl T, Seeböck P, Waldstein SM, Schmidt-Erfurth U, Langs G (2017) Unsupervised anomaly detection with generative adversarial networks to guidemarker discovery. In: International conference on information processing inmedical imaging. Springer, New York, pp 146–157

  13. Yu Q, Kavitha MS, Kurita T. (2019) Detection of one dimensional anomaliesusing a vector-based convolutional autoencoder. In: Asian conference on pattern recognition. Springer, New York, pp 516–529

  14. Fan Y, Wen G, Li D, Qiu S, Levine MD, Xiao F (2020) Video anomaly detection and localization via gaussian mixture fully convolutional variationalautoencoder. Comput Vis Image Underst pp 102920

  15. Kumagai A, Iwata T, Fujiwara Y (2019) Transfer anomaly detection by inferring latent domain representations. In: Advances in neural information processing systems, pp 2467–2477

  16. Otomo K, Kobayashi S, Fukuda K, Esaki H (2019) Latent variable basedanomaly detection in network system logs. IEICE Trans Inform Syst 102(9):1644–1652

    Article  Google Scholar 

  17. Jacobs RA, Jordan MI, Nowlan SJ, Hinton GE (1991) Adaptive mixturesof local experts. Neural Comput 3(1):79–87

    Article  Google Scholar 

  18. Zhao B, Fei-Fei L, Xing EP (2011) Online detection of unusual events in videosvia dynamic sparse coding. In: CVPR, IEEE, pp 3313–3320

  19. Cong Y, Yuan J, Liu J (2011) Sparse reconstruction cost for abnormal eventdetection. In: CVPR IEEE, pp 3449–3456

  20. Perera P, Nallapati R, Xiang B (2019) Ocgan: One-class novelty detection usinggans with constrained latent representations. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2898–2906

  21. Slavic G, Campo D, Baydoun M, Marin P, Martin D, marcenaro L, Regazzoni C (2020) Anomaly detection in video data based on probabilistic latentspace models, arXiv:2003.07623

  22. Beggel L, Pfeiffer M, Bischl B (2019) Robust anomaly detection in images using adversarial autoencoders, arXiv:1901.06355

  23. Fan H, Zhang F, Wang R, Xi L, Li Z (2020) Correlation-aware deep generativemodel for unsupervised anomaly detection. In: Pacific-asia conference onknowledge discovery and data mining. Springer, New York, pp 688–700

  24. Nun I, Protopapas P, Sim B, Chen W (2016) Ensemble learning method foroutlier detection and its application to astronomical light curves. The As-tronomical J 152(3):71

    Google Scholar 

  25. Kurita T, Takahashi T (2003) Viewpoint independent face recognition by competition of the viewpoint dependent classifiers. Neurocomputing 51:181–195

    Article  Google Scholar 

  26. Krizhevsky A, Hinton G, et al. (2009) Learning multiple layers of features fromtiny images

  27. Coates A, Ng A, Lee H (2011) An analysis of single-layer networks in unsupervised feature learning pp 215–223

  28. Yang X, Latecki LJ, Pokrajac D (2009) Outlier detection with globally opti-mal exemplar-based gmm. In: Proceedings of the 2009 SIAM international conference on data mining, SIAM, pp 145–154

  29. Zheng Z, Jeong H-Y, Huang T, Shu J (2017) Kde based outlier detection ondistributed data streams in multimedia network. Multimed Tools Appl 76(17):18027–18045

    Article  Google Scholar 

  30. Chen M, Shi X, Zhang Y, Wu D, Guizani M (2017) Deep features learningfor medical image analysis with convolutional autoencoder neural network, IEEE Transactions on Big Data

  31. Kingma DP, Welling M (2013) Auto-encoding variational bayes, arXiv:1312.6114

  32. Van den Oord A, Kalchbrenner N, Espeholt L, Vinyals O, graves A, et al. (2016) Conditional image generation with pixelcnn decoders. In: Advancesin neural information processing systems, 2016, pp 4790–4798

  33. Akçay S, Atapour-Abarghouei A, Breckon TP (2019) Skip-ganomaly: Skip connected and adversarially trained encoder-decoder anomaly detection. In: 2019 international joint conference on neural networks (IJCNN), IEEE, 2019, pp 1–8

Download references

Author information

Authors and Affiliations

  1. Department of Information Engineering, Hiroshima University, Higashi-hiroshima, Hiroshima, 739-8521, Japan

    Qien Yu

  2. Graduate School of Advanced Science and Engineering, Hiroshima University, Higashi-hiroshima, Hiroshima, 739-8521, Japan

    Muthu Subash Kavitha & Takio Kurita

Authors
  1. Qien Yu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Muthu Subash Kavitha
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Takio Kurita
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Takio Kurita.

Ethics declarations

Conflict of interests

The authors declare that they have no conflict of interest.

Additional information

Ackknowledgement

This work was partly supported by JSPS KAKENHI Grant Number 16K00239.

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Yu, Q., Kavitha, M.S. & Kurita, T. Mixture of experts with convolutional and variational autoencoders for anomaly detection. Appl Intell 51, 3241–3254 (2021). https://doi.org/10.1007/s10489-020-01944-5

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10489-020-01944-5

Keywords

Search

Navigation