Improving autoencoder by mutual information maximization and shuffle attention for novelty detection | Applied Intelligence Skip to main content
Springer Nature Link
Log in

Improving autoencoder by mutual information maximization and shuffle attention for novelty detection

  • Published:
Applied Intelligence Aims and scope Submit manuscript

Abstract

Under an open dynamic environment, a challenging task in object detection is to determine whether samples belong to a known class. Novelty detection can be exploited to identify classes that have not appeared in training process, that is, unknown classes. Current methods mainly adopt autoencoder (AE) to model inlier samples to generate reconstructions of specified categories and distinguish them from outlier samples by the reconstruction error. However, the AE generalizes well to construct images outside of the distribution of the training data, and it makes the model challenging to differentiate inlier samples from outlier samples. To this end, we propose a novelty detection model based on shuffle attention mechanism and mutual information maximization (MIM) to modify the effect of traditional AE on the reconstruction of inlier and outlier samples. Firstly, the rotated inlier samples are reconstructed and classified to enhance the mutual information between latent codes and inlier samples, thus constraining the representation of the latent space. Subsequently, the efficient shuffle attention mechanism is introduced to enable the model to focus more on inlier representation with negligible computation. Experimental results on four public datasets verify the potential performance of the proposed method for novelty detection.

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

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
¥17,985 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price includes VAT (Japan)

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Algorithm 1
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

Notes

  1. Source code is made available at https://github.com/kmoonsl/Improving-AE-by-MIM-SA.

References

  1. Janai J, Güney F, Behl A, Geiger A (2020) Computer vision for autonomous vehicles: problems, datasets and state of the art. Foundations and Trends®; in Computer Graphics and Vision 12(1–3):1–308. https://doi.org/10.1561/0600000079

    Article  Google Scholar 

  2. Randhawa K, Loo CK, Seera M, Lim CP, Nandi AK (2018) Credit card fraud detection using adaboost and majority voting. IEEE access 6:14277–14284. https://doi.org/10.1109/ACCESS.2018.2806420

    Article  Google Scholar 

  3. Oza P, Patel VM (2019) Active authentication using an autoencoder regularized cnn-based one-class classifier. In: Proceedings of the 14th IEEE international conference on automatic face & gesture recognition, pp 1–8. https://doi.org/10.1109/FG.2019.8756525

  4. Perera P, Patel VM (2018) Dual-minimax probability machines for one-class mobile active authentication. In: Proceedings of the 9th IEEE international conference on biometrics theory, applications and systems, pp 1–8. https://doi.org/10.1109/BTAS.2018.8698603

  5. Baur C, Wiestler B, Albarqouni S et al (2018) Deep autoencoding models for unsupervised anomaly segmentation in brain MR images. In: Proceedings of the international MICCAI brainlesion workshop, pp 161–169. https://doi.org/10.1007/978-3-030-11723-8_16

  6. Migdadi L, Telfah A, Hergenröder R, et al. (2022) Novelty detection for metabolic dynamics established on breast cancer tissue using 2D NMR TOCSY spectra. Comput Struc Biotechnol J 20:2965–2977. https://doi.org/10.1016/j.csbj.2022.05.050

    Article  Google Scholar 

  7. Aldweesh A, Derhab A, Emam AZ (2020) Deep learning approaches for anomaly-based intrusion detection systems: a survey, taxonomy, and open issues. Knowls-Based Syst 189:105–124. https://doi.org/10.1016/j.knosys.2019.105124

    Google Scholar 

  8. Golan I, El-Yaniv R (2018) Deep anomaly detection using geometric transformations. In: Proceedings of the 32nd international conference on neural information processing systems, pp 9781–9791

  9. Han K, Rebuffi SA, Ehrhardt S et al (2020) Automatically discovering and learning new visual categories with ranking statistics. In: Proceedings of the 8th intennational conference on learning representations. https://doi.org/10.48550/arXiv.2002.05714

  10. Sultani W, Chen C, Shah M (2018) Real-world anomaly detection in surveillance videos. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 6479–6488

  11. Sabokrou M, Khalooei M, Fathy M, Adeli E (2018) Adversarially learned one-class classifier for novelty detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3379–3388

  12. Goodfellow I, Pouget-Abadie J, Me M, Xu B, Warde-Farley D, Ozair S, Courville A, Bengio Y (2014) Generative adversarial nets. In: Advances in neural information processing systems, pp 2672–2680

  13. Zhang Y, Zhou B, Ding X, et al. (2021) Adversarially learned one-class novelty detection with confidence estimation. Inform Sci 552:48–64. https://doi.org/10.1016/j.ins.2020.11.052

    Article  MathSciNet  MATH  Google Scholar 

  14. Perera P, Nallapati R, Xiang B (2019) Ocgan: one-class novelty detection using gans with constrained latent representations. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 2898–2906. https://doi.org/10.1109/CVPR.2019.00301

  15. Gidaris S, Singh P, Komodakis N (2018) Unsupervised representation learning by predicting image rotations. In: proceedings of the international conference on learning representations. https://doi.org/10.48550/arXiv.1803.07728

  16. Chen X, Duan Y, Houthooft R, Schulman J, Sutskever I, Abbeel P (2016) InfoGAN: interpretable representation learning by information maximizing generative adversarial nets. In: Advances in neural information processing systems. https://doi.org/10.48550/arXiv.1606.03657

  17. Zhang QL, Yang YB (2021) Sa-net: shuffle attention for deep convolutional neural networks. In: Proceedings of the IEEE international conference on acoustics, speech and signal processing, pp 2235–2239. https://doi.org/10.1109/ICASSP39728.2021.9414568

  18. Christopher MB (2006) Pattern recognition and machine learning. Springer, Berlin

    MATH  Google Scholar 

  19. Yin L, Wang H, Fan W (2018) Active learning based support vector data description method for robust novelty detection. Knowl-Based Syst 153:40–52. https://doi.org/10.1016/j.knosys.2018.04.020

    Article  Google Scholar 

  20. Sarmadi H, Karamodin A (2020) A novel anomaly detection method based on adaptive Mahalanobis-squared distance and one-class kNN rule for structural health monitoring under environmental effects. Mech Syst Signal Process 140:1–24. https://doi.org/10.1016/j.ymssp.2019.106495

    Article  Google Scholar 

  21. Zhang Z, Zhu M, Qiu J et al (2019) Outlier detection based on cluster outlier factor and mutual density. In: Proceedings of the international symposium on intelligence computation and applications, pp 91–108. https://doi.org/10.1504/IJIIDS.2019.102329

  22. Deecke L, Vandermeulen R, Ruff L et al (2018) Anomaly detection with generative adversarial networks. In: Proceedings of the international conference on learning representations. https://openreview.net/forum?id=S1EfylZ0Z

  23. Hayashi T, Fujita H, Hernandez-Matamoros A (2021) Less complexity one-class classification approach using construction error of convolutional image transformation network. Inform Sci 560:217–234. https://doi.org/10.1016/j.ins.2021.01.069

    Article  MathSciNet  Google Scholar 

  24. Schlegl T, Seeböck P, Waldstein SM et al (2017) Unsupervised anomaly detection with generative adversarial networks to guide marker discovery. In: Proceedings of the international conference on information processing in medical imaging, pp 146–157. https://doi.org/10.1007/978-3-319-59050-9_12

  25. Zhang Z, Chen S, Sun L (2020) P-kdgan: progressive knowledge distillation with GANs for one-class novelty detection. In: Proceedings of the 29th international joint conference on artificial intelligence, pp 3237–3243. https://doi.org/10.24963/ijcai.2020/448

  26. Jewell JT, Khazaie VR, Mohsenzadeh Y (2022) Oled: one-class learned encoder-decoder network with adversarial context masking for novelty detection. In: Proceedings of the IEEE/CVF winter conference on applications of computer vision, pp 3591–3601. https://doi.org/10.48550/arXiv.2103.14953

  27. Kim KH, Shim S, Lim Y, Jeon J, Choi J, Kim B, Yoon A (2020) Rapp: novelty detection with reconstruction along projection pathway. In: Proceedings of the international conference on learning representations

  28. Shin SY, Kim HJ (2020) Extended autoencoder for novelty detection with reconstruction along projection pathway. Appl Sci 10(13):4497. https://doi.org/10.3390/app10134497

    Article  Google Scholar 

  29. Salehi M, Arya A, Pajoum B, et al. (2021) Arae: adversarially robust training of autoencoders improves novelty detection. Neural Netw 144:726–736. https://doi.org/10.1016/j.neunet.2021.09.014

    Article  Google Scholar 

  30. Tax DMJ, Duin RPW (2004) Support vector data description. Mach Learn 54(1):45–66. https://doi.org/10.1023/B%3AMACH.0000008084.60811.49

    Article  MATH  Google Scholar 

  31. Mirza M, Osindero S (2014) Conditional generative adversarial nets. https://doi.org/10.48550/arXiv.1411.1784

  32. Tian M, Guo D, Cui Y, Pan X, Chen S (2021) Improving auto-encoder novelty detection using channel attention and entropy minimization. In: Proceedings of the 2nd ACM international conference on multimedia in asia, pp 1–6. https://doi.org/10.1145/3444685.3446311

  33. Tian M, Cui Y, Long H, Li J (2021) Improving novelty detection by self-supervised learning and channel attention mechanism. Ind Robot 48(5):673–679. https://doi.org/10.1108/IR-10-2020-0241

    Article  Google Scholar 

  34. Pidhorskyi S, Almohsen R, Doretto G (2018) Generative probabilistic novelty detection with adversarial autoencoders. In: Proceedings of the 32nd international conference on neural information processing systems, pp 6823–6834. https://doi.org/10.48550/arXiv.1807.02588

  35. Chen T, Kornblith S, Norouzi M, et al. (2020) A simple framework for contrastive learning of visual representations. In: Proceedings of the international conference on machine learning, pp 1597–1607. https://doi.org/10.48550/arXiv.2002.05709

  36. Makhzani A, Shlens J, Jaitly N et al (2016) Adversarial autoencoders. https://doi.org/10.48550/arXiv.1511.05644

  37. Barber D, Agakov F (2003) The IM algorithm: a variational approach to information maximization. In: Proceedings of the 16th international conference on neural information processing systems, pp 201–208

  38. Ruff L, Vandermeulen R, Goernitz N, Lucas D, Marius K (2018) Deep one-class classification. In: Proceedings of the international conference on machine learning, pp 4393–4402

  39. Abati D, Porrello A, Calderara S, et al. (2019) Latent space autoregression for novelty detection. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 481–490. https://doi.org/10.1109/CVPR.2019.00057

  40. Schölkopf B, Platt JC, Shawe-Taylor J, et al. (2001) Estimating the support of a high-dimensional distribution. Neural Comput 13(7):1443–1471. https://doi.org/10.1162/089976601750264965

    Article  MATH  Google Scholar 

  41. Hadsell R, Chopra S, LeCun Y (2006) Dimensionality reduction by learning an invariant mapping. In: Proceedings of the IEEE computer society conference on computer vision and pattern recognition, pp 1735–1742. https://doi.org/10.1109/CVPR.2006.100

  42. Zong B, Song Q, Min MR et al (2018) Deep autoencoding gaussian mixture model for unsupervised anomaly detection. In: Proceedings of the international conference on learning representations. https://openreview.net/forum?id=BJJLHbb0-

  43. Wang J, Sun S, Yu Y (2019) Multivariate triangular quantile maps for novelty detection. In: Proceedings of the advances in neural information processing systems. https://doi.org/10.5555/3454287.3454742, pp 5061–5071

Download references

Acknowledgements

This work is supported by the Basic Research Project (JCKY2019604C004).

Author information

Authors and Affiliations

  1. College of Computer Science and Technology, Harbin Engineering University, NO.145 Nantong Street, Harbin, 150001, Heilongjiang, China

    Liu Sun, Ming He, Nianbin Wang & Hongbin Wang

Authors
  1. Liu Sun
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Ming He
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Nianbin Wang
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Hongbin Wang
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Ming He.

Additional information

Publisher’s note

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

Rights and permissions

Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Sun, L., He, M., Wang, N. et al. Improving autoencoder by mutual information maximization and shuffle attention for novelty detection. Appl Intell 53, 17747–17761 (2023). https://doi.org/10.1007/s10489-022-04196-7

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10489-022-04196-7

Keywords