Skip to main content
SpringerLink
Log in

Data Invariants to Understand Unsupervised Out-of-Distribution Detection

  • Conference paper
  • First Online:
Computer Vision – ECCV 2022 (ECCV 2022)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 13691))

Included in the following conference series:

Abstract

Unsupervised out-of-distribution (U-OOD) detection has recently attracted much attention due to its importance in mission-critical systems and broader applicability over its supervised counterpart. Despite this increased attention, U-OOD methods suffer from important shortcomings. By performing a large-scale evaluation on different benchmarks and image modalities, we show in this work that most popular state-of-the-art methods are unable to consistently outperform a simple anomaly detector based on pre-trained features and the Mahalanobis distance (MahaAD). A key reason for the inconsistencies of these methods is the lack of a formal description of U-OOD. Motivated by a simple thought experiment, we propose a characterization of U-OOD based on the invariants of the training dataset. We show how this characterization is unknowingly embodied in the top-scoring MahaAD method, thereby explaining its quality. Furthermore, our approach can be used to interpret predictions of U-OOD detectors and provides insights into good practices for evaluating future U-OOD methods.

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

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 89.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 119.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Abati, D., Porrello, A., Calderara, S., Cucchiara, R.: Latent space autoregression for novelty detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 481–490 (2019)

    Google Scholar 

  2. Ahmed, F., Courville, A.: Detecting semantic anomalies. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 3154–3162 (2020)

    Google Scholar 

  3. Akcay, S., Atapour-Abarghouei, A., Breckon, T.P.: GANomaly: semi-supervised anomaly detection via adversarial training. In: Jawahar, C.V., Li, H., Mori, G., Schindler, K. (eds.) ACCV 2018. LNCS, vol. 11363, pp. 622–637. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-20893-6_39

    Chapter  Google Scholar 

  4. Amodei, D., Olah, C., Steinhardt, J., Christiano, P., Schulman, J., Mané, D.: Concrete problems in AI safety. arXiv preprint arXiv:1606.06565 (2016)

  5. Battikh, M.S., Lenskiy, A.A.: Latent-insensitive autoencoders for anomaly detection and class-incremental learning. arXiv preprint arXiv:2110.13101 (2021)

  6. Bergman, L., Cohen, N., Hoshen, Y.: Deep nearest neighbor anomaly detection. arXiv preprint arXiv:2002.10445 (2020)

  7. Bergman, L., Hoshen, Y.: Classification-based anomaly detection for general data. In: International Conference on Learning Representations (2020)

    Google Scholar 

  8. Bergmann, P., Fauser, M., Sattlegger, D., Steger, C.: Mvtec ad - a comprehensive real-world dataset for unsupervised anomaly detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9592–9600 (2019)

    Google Scholar 

  9. Bozorgtabar, B., Mahapatra, D., Vray, G., Thiran, J.-P.: SALAD: self-supervised aggregation learning for anomaly detection on X-Rays. In: Martel, A.L., et al. (eds.) MICCAI 2020. LNCS, vol. 12261, pp. 468–478. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-59710-8_46

    Chapter  Google Scholar 

  10. Breunig, M.M., Kriegel, H.P., Ng, R.T., Sander, J.: LOF: identifying density-based local outliers. In: Proceedings of the 2000 ACM SIGMOD International Conference on Management of Data, pp. 93–104 (2000)

    Google Scholar 

  11. Chalapathy, R., Chawla, S.: Deep learning for anomaly detection: a survey. arXiv preprint arXiv:1901.03407 (2019)

  12. Choi, H., Jang, E., Alemi, A.A.: Waic, but why? generative ensembles for robust anomaly detection. arXiv preprint arXiv:1810.01392 (2018)

  13. Choi, S., Chung, S.Y.: Novelty detection via blurring. In: International Conference on Learning Representations (2020)

    Google Scholar 

  14. Defard, T., Setkov, A., Loesch, A., Audigier, R.: PaDiM: a patch distribution modeling framework for anomaly detection and localization. In: Del Bimbo, A., et al. (eds.) ICPR 2021. LNCS, vol. 12664, pp. 475–489. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-68799-1_35

    Chapter  Google Scholar 

  15. Golan, I., El-Yaniv, R.: Deep anomaly detection using geometric transformations. In: Advances in Neural Information Processing Systems, pp. 9758–9769 (2018)

    Google Scholar 

  16. Gong, D., et al.: Memorizing normality to detect anomaly: Memory-augmented deep autoencoder for unsupervised anomaly detection. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 1705–1714 (2019)

    Google Scholar 

  17. Gudovskiy, D., Ishizaka, S., Kozuka, K.: Cflow-ad: Real-time unsupervised anomaly detection with localization via conditional normalizing flows. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 98–107 (2022)

    Google Scholar 

  18. Havtorn, J.D.D., Frellsen, J., Hauberg, S., Maaløe, L.: Hierarchical vaes know what they don’t know. In: International Conference on Machine Learning PMLR, pp. 4117–4128 (2021)

    Google Scholar 

  19. Hendrycks, D., Gimpel, K.: A baseline for detecting misclassified and out-of-distribution examples in neural networks. International Conference on Learning Representations (2017)

    Google Scholar 

  20. Hendrycks, D., Mazeika, M., Kadavath, S., Song, D.: Using self-supervised learning can improve model robustness and uncertainty. Adv. Neural Inf. Process. Syst. 32 (2019)

    Google Scholar 

  21. Hou, J., Zhang, Y., Zhong, Q., Xie, D., Pu, S., Zhou, H.: Divide-and-assemble: learning block-wise memory for unsupervised anomaly detection. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 8791–8800 (2021)

    Google Scholar 

  22. Hsu, Y.C., Shen, Y., Jin, H., Kira, Z.: Generalized odin: detecting out-of-distribution image without learning from out-of-distribution data. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10951–10960 (2020)

    Google Scholar 

  23. Kamoi, R., Kobayashi, K.: Why is the mahalanobis distance effective for anomaly detection? arXiv preprint arXiv:2003.00402 (2020)

  24. Kingma, D.P., Dhariwal, P.: Glow: generative flow with invertible 1 \(\times \) 1 convolutions. Adv. Neural Inf. Process. Syst. 31 (2018)

    Google Scholar 

  25. Koner, R., Sinhamahapatra, P., Roscher, K., Günnemann, S., Tresp, V.: Oodformer: Out-of-distribution detection transformer. arXiv preprint arXiv:2107.08976 (2021)

  26. Ledoit, O., Wolf, M.: A well-conditioned estimator for large-dimensional covariance matrices. J. Multivariate Anal. 88(2), 365–411 (2004)

    Article  MathSciNet  Google Scholar 

  27. Lee, K., Lee, K., Lee, H., Shin, J.: A simple unified framework for detecting out-of-distribution samples and adversarial attacks. Adv. Neural Inf. Process. Syst. 31, 7167–7177 (2018)

    Google Scholar 

  28. Li, C.L., Sohn, K., Yoon, J., Pfister, T.: Cutpaste: self-supervised learning for anomaly detection and localization. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9664–9674 (2021)

    Google Scholar 

  29. Liang, S., Li, Y., Srikant, R.: Enhancing the reliability of out-of-distribution image detection in neural networks. In: International Conference on Learning Representations (2018)

    Google Scholar 

  30. Liu, F.T., Ting, K.M., Zhou, Z.H.: Isolation forest. In: 2008 Eighth IEEE International Conference on Data Mining, pp. 413–422. IEEE (2008)

    Google Scholar 

  31. Márquez-Neila, P., Sznitman, R.: Image data validation for medical systems. In: Shen, D. (ed.) MICCAI 2019. LNCS, vol. 11767, pp. 329–337. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32251-9_36

    Chapter  Google Scholar 

  32. Mesarcik, M., Ranguelova, E., Boonstra, A.J., van Nieuwpoort, R.V.: Improving novelty detection using the reconstructions of nearest neighbours. arXiv preprint arXiv:2111.06150 (2021)

  33. Mohseni, S., Vahdat, A., Yadawa, J.: Multi-task transformation learning for robust out-of-distribution detection. arXiv preprint arXiv:2106.03899 (2021)

  34. Morningstar, W., Ham, C., Gallagher, A., Lakshminarayanan, B., Alemi, A., Dillon, J.: Density of states estimation for out of distribution detection. In: International Conference on Artificial Intelligence and Statistics PMLR, pp. 3232–3240 (2021)

    Google Scholar 

  35. Nalisnick, E., Matsukawa, A., Teh, Y.W., Gorur, D., Lakshminarayanan, B.: Do deep generative models know what they don’t know? arXiv preprint arXiv:1810.09136 (2018)

  36. Ouardini, K., et al.: Towards practical unsupervised anomaly detection on retinal images. In: Wang, Q., et al. (eds.) DART/MIL3ID -2019. LNCS, vol. 11795, pp. 225–234. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-33391-1_26

    Chapter  Google Scholar 

  37. Perera, P., Nallapati, R., Xiang, B.: 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 (2019)

    Google Scholar 

  38. Perera, P., Oza, P., Patel, V.M.: One-class classification: A survey. arXiv preprint arXiv:2101.03064 (2021)

  39. Podolskiy, A., Lipin, D., Bout, A., Artemova, E., Piontkovskaya, I.: Revisiting mahalanobis distance for transformer-based out-of-domain detection. arXiv preprint arXiv:2101.03778 (2021)

  40. Reiss, T., Cohen, N., Bergman, L., Hoshen, Y.: Panda: adapting pretrained features for anomaly detection and segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2806–2814 (2021)

    Google Scholar 

  41. Reiss, T., Hoshen, Y.: Mean-shifted contrastive loss for anomaly detection. arXiv preprint arXiv:2106.03844 (2021)

  42. Ren, J., et al.: Likelihood ratios for out-of-distribution detection. Adv. Neural Inf. Process. Syst. 14707–14718 (2019)

    Google Scholar 

  43. Rippel, O., Mertens, P., Merhof, D.: Modeling the distribution of normal data in pre-trained deep features for anomaly detection. In: 2020 25th International Conference on Pattern Recognition (ICPR), pp. 6726–6733. IEEE (2021)

    Google Scholar 

  44. Ruff, L., et al.: A unifying review of deep and shallow anomaly detection. Proc. IEEE 109(5), 756–795 (2021)

    Google Scholar 

  45. Ruff, L., et al.: Deep one-class classification. In: International Conference on Machine Learning PMLR, pp. 4393–4402 (2018)

    Google Scholar 

  46. Sakurada, M., Yairi, T.: Anomaly detection using autoencoders with nonlinear dimensionality reduction. In: Proceedings of the MLSDA 2014 2nd Workshop on Machine Learning for Sensory Data Analysis, pp. 4–11 (2014)

    Google Scholar 

  47. Salehi, M., Eftekhar, A., Sadjadi, N., Rohban, M.H., Rabiee, H.R.: Puzzle-ae: Novelty detection in images through solving puzzles. arXiv preprint arXiv:2008.12959 (2020)

  48. Salehi, M., Sadjadi, N., Baselizadeh, S., Rohban, M.H., Rabiee, H.R.: Multiresolution knowledge distillation for anomaly detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 14902–14912 (2021)

    Google Scholar 

  49. Salimans, T., Karpathy, A., Chen, X., Kingma, D.P.: Pixelcnn++: improving the pixelcnn with discretized logistic mixture likelihood and other modifications. In: International Conference on Learning Representations (2017)

    Google Scholar 

  50. Sastry, C.S., Oore, S.: Detecting out-of-distribution examples with gram matrices. In: International Conference on Machine Learning PMLR, pp. 8491–8501 (2020)

    Google Scholar 

  51. Schirrmeister, R., Zhou, Y., Ball, T., Zhang, D.: Understanding anomaly detection with deep invertible networks through hierarchies of distributions and features. Adv. Neural Inf. Process. Syst. 33, 21038–21049 (2020)

    Google Scholar 

  52. Schölkopf, B., Williamson, R.C., Smola, A.J., Shawe-Taylor, J., Platt, J.C., et al.: Support vector method for novelty detection. In: NIPS, vol. 12, pp. 582–588. Citeseer (1999)

    Google Scholar 

  53. Sehwag, V., Chiang, M., Mittal, P.: Ssd: a unified framework for self-supervised outlier detection. In: International Conference on Learning Representations (2021)

    Google Scholar 

  54. Serrà, J., Álvarez, D., Gómez, V., Slizovskaia, O., Núñez, J.F., Luque, J.: Input complexity and out-of-distribution detection with likelihood-based generative models. In: International Conference on Learning Representations (2019)

    Google Scholar 

  55. Sohn, K., Li, C.L., Yoon, J., Jin, M., Pfister, T.: Learning and evaluating representations for deep one-class classification. In: International Conference on Learning Representations (2021)

    Google Scholar 

  56. Tack, J., Mo, S., Jeong, J., Shin, J.: CSI: Novelty detection via contrastive learning on distributionally shifted instances. Adv. Neural Inf. Process. Syst. 33, 11839–11852 (2020)

    Google Scholar 

  57. Tang, Y.X., Tang, Y.B., Han, M., Xiao, J., Summers, R.M.: Abnormal chest x-ray identification with generative adversarial one-class classifier. In: 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), pp. 1358–1361. IEEE (2019)

    Google Scholar 

  58. Wang, S., et al.: Effective end-to-end unsupervised outlier detection via inlier priority of discriminative network. In: Advances in Neural Information Processing Systems, pp. 5962–5975 (2019)

    Google Scholar 

  59. Xiao, Z., Yan, Q., Amit, Y.: Do we really need to learn representations from in-domain data for outlier detection? In: ICML 2021 Workshop on Uncertainty & Robustness in Deep Learning (2021)

    Google Scholar 

  60. Yang, J., Zhou, K., Li, Y., Liu, Z.: Generalized out-of-distribution detection: A survey. arXiv preprint arXiv:2110.11334 (2021)

  61. Zong, B., Song, Q., Min, M.R., Cheng, W., Lumezanu, C., Cho, D., Chen, H.: Deep autoencoding gaussian mixture model for unsupervised anomaly detection. In: International conference on learning representations (2018)

    Google Scholar 

Download references

Acknowledgements

This work was funded by the Swiss National Science Foundation (SNSF), research grant 200021_192285 “Image data validation for AI systems”.

Author information

Authors and Affiliations

  1. University of Bern, Bern, Switzerland

    Lars Doorenbos, Raphael Sznitman & Pablo Márquez-Neila

Authors
  1. Lars Doorenbos
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Raphael Sznitman
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Pablo Márquez-Neila
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Lars Doorenbos .

Editor information

Editors and Affiliations

  1. Tel Aviv University, Tel Aviv, Israel

    Shai Avidan

  2. University College London, London, UK

    Gabriel Brostow

  3. Google AI, Accra, Ghana

    Moustapha Cissé

  4. University of Catania, Catania, Italy

    Giovanni Maria Farinella

  5. Facebook (United States), Menlo Park, CA, USA

    Tal Hassner

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 230 KB)

Rights and permissions

Reprints and permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Doorenbos, L., Sznitman, R., Márquez-Neila, P. (2022). Data Invariants to Understand Unsupervised Out-of-Distribution Detection. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds) Computer Vision – ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, vol 13691. Springer, Cham. https://doi.org/10.1007/978-3-031-19821-2_8

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-19821-2_8

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-19820-5

  • Online ISBN: 978-3-031-19821-2

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation