Advertisement

Image Anomaly Detection with Generative Adversarial Networks

  • Lucas DeeckeEmail author
  • Robert Vandermeulen
  • Lukas Ruff
  • Stephan Mandt
  • Marius Kloft
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11051)

Abstract

Many anomaly detection methods exist that perform well on low-dimensional problems however there is a notable lack of effective methods for high-dimensional spaces, such as images. Inspired by recent successes in deep learning we propose a novel approach to anomaly detection using generative adversarial networks. Given a sample under consideration, our method is based on searching for a good representation of that sample in the latent space of the generator; if such a representation is not found, the sample is deemed anomalous. We achieve state-of-the-art performance on standard image benchmark datasets and visual inspection of the most anomalous samples reveals that our method does indeed return anomalies.

Notes

Acknowledgments

We kindly thank reviewers for their constructive feedback, which helped to improve this work. LD gratefully acknowledges funding from the School of Informatics, University of Edinburgh. LR acknowledges financial support from the German Federal Ministry of Transport and Digital Infrastructure (BMVI) in the project OSIMAB (FKZ: 19F2017E). MK and RV acknowledge support from the German Research Foundation (DFG) award KL 2698/2-1 and from the Federal Ministry of Science and Education (BMBF) award 031B0187B.

References

  1. 1.
    Arjovsky, M., Bottou, L.: Towards principled methods for training generative adversarial networks. In: International Conference on Learning Representations (2017)Google Scholar
  2. 2.
    Arjovsky, M., Chintala, S., Bottou, L.: Wasserstein generative adversarial networks. In: International Conference on Machine Learning, pp. 214–223 (2017)Google Scholar
  3. 3.
    Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. In: International Conference on Learning Representations (2015)Google Scholar
  4. 4.
    Bojanowski, P., Joulin, A., Lopez-Paz, D., Szlam, A.: Optimizing the latent space of generative networks. In: International Conference on Machine Learning (2018)Google Scholar
  5. 5.
    Campbell, C., Bennett, K.P.: A linear programming approach to novelty detection. In: Advances in Neural Information Processing Systems, pp. 395–401 (2001)Google Scholar
  6. 6.
    Chandola, V., Banerjee, A., Kumar, V.: Anomaly detection: a survey. ACM Comput. Surv. (CSUR) 41(3), 15 (2009)CrossRefGoogle Scholar
  7. 7.
    Creswell, A., Bharath, A.A.: Inverting the generator of a generative adversarial network. arXiv preprint arXiv:1611.05644 (2016)
  8. 8.
    Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: Computer Vision and Pattern Recognition, pp. 248–255. IEEE (2009)Google Scholar
  9. 9.
    Donahue, J., Krähenbühl, P., Darrell, T.: Adversarial feature learning. In: International Conference on Learning Representations (2017)Google Scholar
  10. 10.
    Dumoulin, V., et al.: Adversarially learned inference. In: International Conference on Learning Representations (2017)Google Scholar
  11. 11.
    Dutta, H., Giannella, C., Borne, K., Kargupta, H.: Distributed top-k outlier detection from astronomy catalogs using the DEMAC system. In: International Conference on Data Mining, pp. 473–478. SIAM (2007)Google Scholar
  12. 12.
    Edgeworth, F.: XLI. on discordant observations. Lond. Edinb. Dublin Philos. Mag. J. Sci. 23(143), 364–375 (1887)CrossRefGoogle Scholar
  13. 13.
    Emmott, A.F., Das, S., Dietterich, T., Fern, A., Wong, W.K.: Systematic construction of anomaly detection benchmarks from real data. In: ACM SIGKDD Workshop on Outlier Detection and Description, pp. 16–21. ACM (2013)Google Scholar
  14. 14.
    Erfani, S.M., Rajasegarar, S., Karunasekera, S., Leckie, C.: High-dimensional and large-scale anomaly detection using a linear one-class SVM with deep learning. Pattern Recognit. 58, 121–134 (2016)CrossRefGoogle Scholar
  15. 15.
    Eskin, E.: Anomaly detection over noisy data using learned probability distributions. In: International Conference on Machine Learning (2000)Google Scholar
  16. 16.
    Evangelista, P.F., Embrechts, M.J., Szymanski, B.K.: Some properties of the gaussian kernel for one class learning. In: de Sá, J.M., Alexandre, L.A., Duch, W., Mandic, D. (eds.) ICANN 2007. LNCS, vol. 4668, pp. 269–278. Springer, Heidelberg (2007).  https://doi.org/10.1007/978-3-540-74690-4_28CrossRefGoogle Scholar
  17. 17.
    Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, pp. 2672–2680 (2014)Google Scholar
  18. 18.
    Görnitz, N., Braun, M., Kloft, M.: Hidden Markov anomaly detection. In: International Conference on Machine Learning, pp. 1833–1842 (2015)Google Scholar
  19. 19.
    Hu, W., Liao, Y., Vemuri, V.R.: Robust anomaly detection using support vector machines. In: International Conference on Machine Learning, pp. 282–289 (2003)Google Scholar
  20. 20.
    Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine Learning, pp. 448–456 (2015)Google Scholar
  21. 21.
    Kingma, D., Ba, J.: Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
  22. 22.
    Kingma, D.P., Welling, M.: Auto-encoding variational Bayes. arXiv preprint arXiv:1312.6114 (2013)
  23. 23.
    Krizhevsky, A., Hinton, G.: Learning multiple layers of features from tiny images. Technical report, University of Toronto (2009)Google Scholar
  24. 24.
    Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)Google Scholar
  25. 25.
    Le, Q., Mikolov, T.: Distributed representations of sentences and documents. In: International Conference on Machine Learning, pp. 1188–1196 (2014)Google Scholar
  26. 26.
    LeCun, Y.: The MNIST database of handwritten digits (1998). http://yann.lecun.com/exdb/mnist
  27. 27.
    Li, Y., Swersky, K., Zemel, R.: Generative moment matching networks. In: International Conference on Machine Learning, pp. 1718–1727 (2015)Google Scholar
  28. 28.
    Ling, H., Okada, K.: Diffusion distance for histogram comparison. In: Computer Vision and Pattern Recognition, pp. 246–253. IEEE (2006)Google Scholar
  29. 29.
    Lipton, Z.C., Tripathi, S.: Precise recovery of latent vectors from generative adversarial networks. In: International Conference on Learning Representations, Workshop Track (2017)Google Scholar
  30. 30.
    Liu, F.T., Ting, K.M., Zhou, Z.H.: Isolation forest. In: International Conference on Data Mining, pp. 413–422. IEEE (2008)Google Scholar
  31. 31.
    Lopez-Paz, D., Oquab, M.: Revisiting classifier two-sample tests. In: International Conference on Learning Representations (2017)Google Scholar
  32. 32.
    Mao, X., Li, Q., Xie, H., Lau, R.Y., Wang, Z., Smolley, S.P.: Least squares generative adversarial networks. In: International Conference on Computer Vision, pp. 2794–2802. IEEE (2017)Google Scholar
  33. 33.
    Masci, J., Meier, U., Cireşan, D., Schmidhuber, J.: Stacked convolutional auto-encoders for hierarchical feature extraction. Artificial Neural Networks and Machine Learning (ICANN), pp. 52–59 (2011)Google Scholar
  34. 34.
    Metz, L., Poole, B., Pfau, D., Sohl-Dickstein, J.: Unrolled generative adversarial networks. In: International Conference on Learning Representations (2017)Google Scholar
  35. 35.
    Müller, A.: Integral probability metrics and their generating classes of functions. Adv. Appl. Probab. 29(2), 429–443 (1997)MathSciNetCrossRefGoogle Scholar
  36. 36.
    Narayanan, H., Mitter, S.: Sample complexity of testing the manifold hypothesis. In: Advances in Neural Information Processing Systems, pp. 1786–1794 (2010)Google Scholar
  37. 37.
    Nowozin, S., Cseke, B., Tomioka, R.: f-GAN: training generative neural samplers using variational divergence minimization. In: Advances in Neural Information Processing Systems, pp. 271–279 (2016)Google Scholar
  38. 38.
    Odena, A., Dumoulin, V., Olah, C.: Deconvolution and checkerboard artifacts. Distill 1(10), e3 (2016)Google Scholar
  39. 39.
    Ourston, D., Matzner, S., Stump, W., Hopkins, B.: Applications of hidden Markov models to detecting multi-stage network attacks. In: Proceedings of the 36th Annual Hawaii International Conference on System Sciences. IEEE (2003)Google Scholar
  40. 40.
    Parzen, E.: On estimation of a probability density function and mode. Ann. Math. Stat. 33(3), 1065–1076 (1962)MathSciNetCrossRefGoogle Scholar
  41. 41.
    Pearson, K.: On lines and planes of closest fit to systems of points in space. Philos. Mag. 2(11), 559–572 (1901)CrossRefGoogle Scholar
  42. 42.
    Pelleg, D., Moore, A.W.: Active learning for anomaly and rare-category detection. In: Advances in Neural Information Processing Systems, pp. 1073–1080 (2005)Google Scholar
  43. 43.
    Protopapas, P., Giammarco, J., Faccioli, L., Struble, M., Dave, R., Alcock, C.: Finding outlier light curves in catalogues of periodic variable stars. Mon. Not. R. Astron. Soc. 369(2), 677–696 (2006)CrossRefGoogle Scholar
  44. 44.
    Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv preprint arXiv:1511.06434 (2015)
  45. 45.
    Ruff, L., et al.: Deep one-class classification. In: International Conference on Machine Learning (2018)Google Scholar
  46. 46.
    Schlegl, T., Seeböck, P., Waldstein, S.M., Schmidt-Erfurth, U., Langs, G.: Unsupervised anomaly detection with generative adversarial networks to guide marker discovery. In: Niethammer, M., et al. (eds.) IPMI 2017. LNCS, vol. 10265, pp. 146–157. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-59050-9_12CrossRefGoogle Scholar
  47. 47.
    Schölkopf, B., Platt, J.C., Shawe-Taylor, J., Smola, A.J., Williamson, R.C.: Estimating the support of a high-dimensional distribution. Technical report MSR-TR-99-87, Microsoft Research (1999)Google Scholar
  48. 48.
    Singliar, T., Hauskrecht, M.: Towards a learning traffic incident detection system. In: Workshop on Machine Learning Algorithms for Surveillance and Event Detection, International Conference on Machine Learning (2006)Google Scholar
  49. 49.
    Sriperumbudur, B.K., Fukumizu, K., Gretton, A., Schölkopf, B., Lanckriet, G.R.: On integral probability metrics, \(\phi \)-divergences and binary classification. arXiv preprint arXiv:0901.2698 (2009)
  50. 50.
    Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: Advances in Neural Information Processing Systems, pp. 3104–3112 (2014)Google Scholar
  51. 51.
    Wong, W.K., Moore, A.W., Cooper, G.F., Wagner, M.M.: Bayesian network anomaly pattern detection for disease outbreaks. In: International Conference on Machine Learning, pp. 808–815 (2003)Google Scholar
  52. 52.
    Xiao, J., Hays, J., Ehinger, K.A., Oliva, A., Torralba, A.: Sun database: large-scale scene recognition from abbey to zoo. In: Computer Vision and Pattern Recognition, pp. 3485–3492. IEEE (2010)Google Scholar
  53. 53.
    Yeung, D.Y., Chow, C.: Parzen-window network intrusion detectors. In: International Conference on Pattern Recognition, vol. 4, pp. 385–388. IEEE (2002)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Lucas Deecke
    • 1
    Email author
  • Robert Vandermeulen
    • 2
  • Lukas Ruff
    • 3
  • Stephan Mandt
    • 4
  • Marius Kloft
    • 2
  1. 1.University of EdinburghEdinburghScotland, UK
  2. 2.TU KaiserslauternKaiserslauternGermany
  3. 3.Hasso Plattner InstitutePotsdamGermany
  4. 4.University of CaliforniaIrvineUSA

Personalised recommendations