Advertisement

Utilizing Patch-Level Category Activation Patterns for Multiple Class Novelty Detection

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12355)

Abstract

For any recognition system, the ability to identify novel class samples during inference is an important aspect of the system’s robustness. This problem of detecting novel class samples during inference is commonly referred to as Multiple Class Novelty Detection. In this paper, we propose a novel method that makes deep convolutional neural networks robust to novel classes. Specifically, during training one branch performs traditional classification (referred to as global inference), and the other branch provides patch-level information to keep track of the class-specific activation patterns (referred to as local inference). Both global and local branch information are combined to train a novelty detection network, which is used during inference to identify novel classes. We evaluate the proposed method on four datasets (Caltech256, CUB-200, Stanford Dogs and FounderType-200) and show that the proposed method is able to identify novel class samples better compared to the other deep convolutional neural network-based methods.

Keywords

Multiple class novelty detection Class activation patterns 

Notes

Acknowledgement

This work was supported by the NSF grant 1910141.

Supplementary material

504449_1_En_25_MOESM1_ESM.pdf (1.6 mb)
Supplementary material 1 (pdf 1675 KB)

References

  1. 1.
    Baweja, Y., Oza, P., Perera, P., Patel, V.M.: Anomaly detection-based unknown face presentation attack detection. In: International Joint Conference on Biometrics (IJCB), Houston, TX (2020)Google Scholar
  2. 2.
    Bendale, A., Boult, T.E.: Towards open set deep networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1563–1572 (2016)Google Scholar
  3. 3.
    Bhattacharjee, S., Mandal, D., Biswas, S.: Multi-class novelty detection using mix-up technique. In: The IEEE Winter Conference on Applications of Computer Vision, pp. 1400–1409 (2020)Google Scholar
  4. 4.
    Bodesheim, P., Freytag, A., Rodner, E., Denzler, J.: Local novelty detection in multi-class recognition problems. In: 2015 IEEE Winter Conference on Applications of Computer Vision, pp. 813–820. IEEE (2015)Google Scholar
  5. 5.
    Bodesheim, P., Freytag, A., Rodner, E., Kemmler, M., Denzler, J.: Kernel null space methods for novelty detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3374–3381 (2013)Google Scholar
  6. 6.
    Bonawitz, K., et al.: Practical secure aggregation for privacy-preserving machine learning. In: Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security, pp. 1175–1191 (2017)Google Scholar
  7. 7.
    Brendel, W., Bethge, M.: Approximating cnns with bag-of-local-features models works surprisingly well on imagenet. arXiv preprint arXiv:1904.00760 (2019)
  8. 8.
    Carlini, N., Wagner, D.: Towards evaluating the robustness of neural networks. In: 2017 IEEE Symposium on Security and Privacy (SP), pp. 39–57. IEEE (2017)Google Scholar
  9. 9.
    DeVries, T., Taylor, G.W.: Learning confidence for out-of-distribution detection in neural networks. arXiv preprint arXiv:1802.04865 (2018)
  10. 10.
    Dhamija, A.R., Günther, M., Boult, T.E.: Improving deep network robustness to unknown inputs with objectosphere (2019)Google Scholar
  11. 11.
    Eskin, E., Arnold, A., Prerau, M., Portnoy, L., Stolfo, S.: A geometric framework for unsupervised anomaly detection. In: Barbará, D., Jajodia, S. (eds.) Applications of data mining in computer security. Advances in Information Security, vol. 6, pp. 77–101. Springer, Boston (2002).  https://doi.org/10.1007/978-1-4615-0953-0_4CrossRefGoogle Scholar
  12. 12.
    Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572 (2014)
  13. 13.
    Hautamaki, V., Karkkainen, I., Franti, P.: Outlier detection using k-nearest neighbour graph. In: Proceedings of the 17th International Conference on Pattern Recognition, ICPR 2004, vol. 3, pp. 430–433. IEEE (2004)Google Scholar
  14. 14.
    Hendrycks, D., Gimpel, K.: A baseline for detecting misclassified and out-of-distribution examples in neural networks. arXiv preprint arXiv:1610.02136 (2016)
  15. 15.
    Hoffmann, H.: Kernel PCA for novelty detection. Pattern Recogn. 40(3), 863–874 (2007)CrossRefGoogle Scholar
  16. 16.
    Kim, B., Kim, H., Kim, K., Kim, S., Kim, J.: Learning not to learn: training deep neural networks with biased data. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2019Google Scholar
  17. 17.
    Knorr, E.M., Ng, R.T., Tucakov, V.: Distance-based outliers: algorithms and applications. VLDB J. Int. J. Very Large Data Bases 8(3-4), 237–253 (2000)Google Scholar
  18. 18.
    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
  19. 19.
    Liang, S., Li, Y., Srikant, R.: Enhancing the reliability of out-of-distribution image detection in neural networks. arXiv preprint arXiv:1706.02690 (2017)
  20. 20.
    Liu, J., Lian, Z., Wang, Y., Xiao, J.: Incremental kernel null space discriminant analysis for novelty detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 792–800 (2017)Google Scholar
  21. 21.
    Madry, A., Makelov, A., Schmidt, L., Tsipras, D., Vladu, A.: Towards deep learning models resistant to adversarial attacks. arXiv preprint arXiv:1706.06083 (2017)
  22. 22.
    Markou, M., Singh, S.: Novelty detection: a review—part 1: statistical approaches. Signal Process. 83(12), 2481–2497 (2003)Google Scholar
  23. 23.
    Neal, L., Olson, M., Fern, X., Wong, W.-K., Li, F.: Open set learning with counterfactual images. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11210, pp. 620–635. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-01231-1_38CrossRefGoogle Scholar
  24. 24.
    Oza, P., Nguyen, H.V.N., Patel, V.M.: Multiple class novelty detection under data distribution shift. In: ECCV 2020. Springer, Cham (2020)Google Scholar
  25. 25.
    Oza, P., Patel, V.M.: One-class convolutional neural network. IEEE Signal Process. Lett. 26(2), 277–281 (2018)CrossRefGoogle Scholar
  26. 26.
    Perera, P., et al.: Generative-discriminative feature representations for open-set recognition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 11814–11823 (2020)Google Scholar
  27. 27.
    Perera, P., Nallapati, R., Xiang, B.: OCGAN: one-class novelty detection using GANs with constrained latent representations. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2898–2906 (2019)Google Scholar
  28. 28.
    Perera, P., Patel, V.M.: Deep transfer learning for multiple class novelty detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 11544–11552 (2019)Google Scholar
  29. 29.
    Perera, P., Patel, V.M.: Learning deep features for one-class classification. IEEE Trans. Image Process. 28(11), 5450–5463 (2019)MathSciNetCrossRefGoogle Scholar
  30. 30.
    Samangouei, P., Kabkab, M., Chellappa, R.: Defense-GAN: protecting classifiers against adversarial attacks using generative models. arXiv preprint arXiv:1805.06605 (2018)
  31. 31.
    Schölkopf, B., Smola, A.J., Bach, F., et al.: Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond. MIT Press, Cambridge (2002)Google Scholar
  32. 32.
    Schultheiss, A., Käding, C., Freytag, A., Denzler, J.: Finding the unknown: novelty detection with extreme value signatures of deep neural activations. In: Roth, V., Vetter, T. (eds.) GCPR 2017. LNCS, vol. 10496, pp. 226–238. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-66709-6_19CrossRefGoogle Scholar
  33. 33.
    Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-CAM: visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 618–626 (2017)Google Scholar
  34. 34.
    Shao, R., Perera, P., Yuen, P.C., Patel, V.M.: Open-set adversarial defense. In: ECCV 2020. Springer, Cham (2020)Google Scholar
  35. 35.
    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
  36. 36.
    Srinivas, N., Ricanek, K., Michalski, D., Bolme, D.S., King, M.: Face recognition algorithm bias: Performance differences on images of children and adults. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (2019)Google Scholar
  37. 37.
    Szegedy, C., et al.: Intriguing properties of neural networks. arXiv preprint arXiv:1312.6199 (2013)
  38. 38.
    Tax, D.M., Duin, R.P.: Support vector data description. Mach. Learn. 54(1), 45–66 (2004)CrossRefGoogle Scholar
  39. 39.
    Turk, M., Pentland, A.: Eigenfaces for recognition. J. Cogn. Neurosci. 3(1), 71–86 (1991)CrossRefGoogle Scholar
  40. 40.
    Vera-Rodriguez, R., Blazquez, M., Morales, A., Gonzalez-Sosa, E., Neves, J.C., Proenca, H.: Facegenderid: exploiting gender information in dcnns face recognition systems. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (2019)Google Scholar
  41. 41.
    Wright, J., Yang, A.Y., Ganesh, A., Sastry, S.S., Ma, Y.: Robust face recognition via sparse representation. IEEE Trans. Pattern Anal. Mach. Intell. 31(2), 210–227 (2008)CrossRefGoogle Scholar
  42. 42.
    Xia, Y., Cao, X., Wen, F., Hua, G., Sun, J.: Learning discriminative reconstructions for unsupervised outlier removal. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1511–1519 (2015)Google Scholar
  43. 43.
    You, C., Robinson, D.P., Vidal, R.: Provable self-representation based outlier detection in a union of subspaces. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017Google Scholar
  44. 44.
    Zhang, H., Patel, V.M.: Sparse representation-based open set recognition. IEEE Trans. Pattern Anal. Mach. Intell. 39(8), 1690–1696 (2016)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Johns Hopkins UniversityBaltimoreUSA

Personalised recommendations