Skip to main content
SpringerLink
Log in

DICE: Leveraging Sparsification for 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 13684))

Included in the following conference series:

Abstract

Detecting out-of-distribution (OOD) inputs is a central challenge for safely deploying machine learning models in the real world. Previous methods commonly rely on an OOD score derived from the overparameterized weight space, while largely overlooking the role of sparsification. In this paper, we reveal important insights that reliance on unimportant weights and units can directly attribute to the brittleness of OOD detection. To mitigate the issue, we propose a sparsification-based OOD detection framework termed DICE. Our key idea is to rank weights based on a measure of contribution, and selectively use the most salient weights to derive the output for OOD detection. We provide both empirical and theoretical insights, characterizing and explaining the mechanism by which DICE improves OOD detection. By pruning away noisy signals, DICE provably reduces the output variance for OOD data, resulting in a sharper output distribution and stronger separability from ID data. We demonstrate the effectiveness of sparsification-based OOD detection on several benchmarks and establish competitive performance. Code is available at: https://github.com/deeplearning-wisc/dice.git.

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. Ba, J., Frey, B.: Adaptive dropout for training deep neural networks. In: Advances in Neural Information Processing Systems, vol. 26 (2013)

    Google Scholar 

  2. Babaeizadeh, M., Smaragdis, P., Campbell, R.H.: Noiseout: a simple way to prune neural networks. CoRR abs/1611.06211 (2016)

    Google Scholar 

  3. 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 

  4. Bevandić, P., Krešo, I., Oršić, M., Šegvić, S.: Discriminative out-of-distribution detection for semantic segmentation. arXiv preprint. arXiv:1808.07703 (2018)

  5. Chen, J., Li, Y., Wu, X., Liang, Y., Jha, S.: ATOM: robustifying out-of-distribution detection using outlier mining. In: Oliver, N., Pérez-Cruz, F., Kramer, S., Read, J., Lozano, J.A. (eds.) ECML PKDD 2021. LNCS (LNAI), vol. 12977, pp. 430–445. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-86523-8_26

    Chapter  Google Scholar 

  6. Cimpoi, M., Maji, S., Kokkinos, I., Mohamed, S., Vedaldi, A.: Describing textures in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3606–3613 (2014)

    Google Scholar 

  7. Dietterich, T.G., Guyer, A.: The familiarity hypothesis: explaining the behavior of deep open set methods. arXiv preprint. arXiv:2203.02486 (2022)

  8. Du, X., Wang, X., Gozum, G., Li, Y.: Unknown-aware object detection: learning what you don’t know from videos in the wild. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (2022)

    Google Scholar 

  9. Du, X., Wang, Z., Cai, M., Li, Y.: Vos: learning what you don’t know by virtual outlier synthesis. In: Proceedings of the International Conference on Learning Representations (2022)

    Google Scholar 

  10. Filos, A., Tigkas, P., McAllister, R., Rhinehart, N., Levine, S., Gal, Y.: Can autonomous vehicles identify, recover from, and adapt to distribution shifts? In: Proceedings of the International Conference on Machine Learning, pp. 3145–3153. PMLR (2020)

    Google Scholar 

  11. Gal, Y., Ghahramani, Z.: Dropout as a bayesian approximation: Representing model uncertainty in deep learning. In: Proceedings of the International Conference on Machine Learning, pp. 1050–1059 (2016)

    Google Scholar 

  12. Geifman, Y., El-Yaniv, R.: Selectivenet: a deep neural network with an integrated reject option. arXiv preprint. arXiv:1901.09192 (2019)

  13. Gomez, A.N., et al.: Learning sparse networks using targeted dropout. arXiv preprint. arXiv:1905.13678 (2019)

  14. Han, S., Mao, H., Dally, W.J.: Deep compression: compressing deep neural network with pruning, trained quantization and huffman coding. In: Proceedings of the International Conference on Learning Representations (2016)

    Google Scholar 

  15. Han, S., Pool, J., Tran, J., Dally, W.: Learning both weights and connections for efficient neural network. In: Proceedings of the Advances in Neural Information Processing Systems. vol. 28, pp. 1135–1143 (2015)

    Google Scholar 

  16. He, K., Zhang, X., Ren, S., Sun, J.: Identity mappings in deep residual networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 630–645. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46493-0_38

    Chapter  Google Scholar 

  17. Hein, M., Andriushchenko, M., Bitterwolf, J.: Why relu networks yield high-confidence predictions far away from the training data and how to mitigate the problem. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 41–50 (2019)

    Google Scholar 

  18. Hendrycks, D., Dietterich, T.: Benchmarking neural network robustness to common corruptions and perturbations. arXiv preprint. arXiv:1903.12261 (2019)

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

    Google Scholar 

  20. Hendrycks, D., Mazeika, M., Dietterich, T.: Deep anomaly detection with outlier exposure. arXiv preprint. arXiv:1812.04606 (2018)

  21. 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 (2020)

    Google Scholar 

  22. Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700–4708 (2017)

    Google Scholar 

  23. Huang, R., Geng, A., Li, Y.: On the importance of gradients for detecting distributional shifts in the wild. In: Proceedings of the Advances in Neural Information Processing Systems (2021)

    Google Scholar 

  24. Huang, R., Li, Y.: Towards scaling out-of-distribution detection for large semantic space. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (2021)

    Google Scholar 

  25. Jeong, T., Kim, H.: Ood-maml: meta-learning for few-shot out-of-distribution detection and classification. In: Proceedings of the Advances in Neural Information Processing Systems (2020)

    Google Scholar 

  26. Katz-Samuels, J., Nakhleh, J., Nowak, R., Li, Y.: Training ood detectors in their natural habitats. In: Proceedings of the International Conference on Machine Learning. PMLR (2022)

    Google Scholar 

  27. Koh, P.W., et al.: Wilds: a benchmark of in-the-wild distribution shifts. In: Proceedings of the International Conference on Machine Learning, pp. 5637–5664. PMLR (2021)

    Google Scholar 

  28. Krizhevsky, A., Hinton, G., et al.: Learning multiple layers of features from tiny images (2009)

    Google Scholar 

  29. Lakshminarayanan, B., Pritzel, A., Blundell, C.: Simple and scalable predictive uncertainty estimation using deep ensembles. In: Advances in Neural Information Processing Systems, pp. 6402–6413 (2017)

    Google Scholar 

  30. Lee, K., Lee, H., Lee, K., Shin, J.: Training confidence-calibrated classifiers for detecting out-of-distribution samples. arXiv preprint. arXiv:1711.09325 (2017)

  31. Lee, K., Lee, K., Lee, H., Shin, J.: A simple unified framework for detecting out-of-distribution samples and adversarial attacks. In: Advances in Neural Information Processing Systems, pp. 7167–7177 (2018)

    Google Scholar 

  32. Li, H., Kadav, A., Durdanovic, I., Samet, H., Graf, H.P.: Pruning filters for efficient convnets. In: Proceedings of International Conference on Learning Representations (2017)

    Google Scholar 

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

    Google Scholar 

  34. Lin, Z., Roy, S.D., Li, Y.: Mood: multi-level out-of-distribution detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 15313–15323 (2021)

    Google Scholar 

  35. Liu, W., Wang, X., Owens, J., Li, Y.: Energy-based out-of-distribution detection. In: Proceedings of the Advances in Neural Information Processing Systems (2020)

    Google Scholar 

  36. Louizos, C., Welling, M., Kingma, D.P.: Learning sparse neural networks through \(l_0\) regularization. In: International Conference on Learning Representations (2018)

    Google Scholar 

  37. Maddox, W.J., Izmailov, P., Garipov, T., Vetrov, D.P., Wilson, A.G.: A simple baseline for bayesian uncertainty in deep learning. In: Advances in Neural Information Processing Systems, vol. 32, pp. 13153–13164 (2019)

    Google Scholar 

  38. Malinin, A., Gales, M.: Predictive uncertainty estimation via prior networks. In: Advances in Neural Information Processing Systems, pp. 7047–7058 (2018)

    Google Scholar 

  39. Malinin, A., Gales, M.: Reverse kl-divergence training of prior networks: improved uncertainty and adversarial robustness. In: Advances in Neural Information Processing Systems (2019)

    Google Scholar 

  40. Meinke, A., Hein, M.: Towards neural networks that provably know when they don’t know. arXiv preprint. arXiv:1909.12180 (2019)

  41. Ming, Y., Fan, Y., Li, Y.: Poem: out-of-distribution detection with posterior sampling. In: Proceedings of the International Conference on Machine Learning. PMLR (2022)

    Google Scholar 

  42. Mohseni, S., Pitale, M., Yadawa, J., Wang, Z.: Self-supervised learning for generalizable out-of-distribution detection. In: AAAI, pp. 5216–5223 (2020)

    Google Scholar 

  43. Morteza, P., Li, Y.: Provable guarantees for understanding out-of-distribution detection. In: Proceedings of the AAAI Conference on Artificial Intelligence (2022)

    Google Scholar 

  44. Netzer, Y., Wang, T., Coates, A., Bissacco, A., Wu, B., Ng, A.Y.: Reading digits in natural images with unsupervised feature learning (2011)

    Google Scholar 

  45. Nguyen, A., Yosinski, J., Clune, J.: Deep neural networks are easily fooled: high confidence predictions for unrecognizable images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 427–436 (2015)

    Google Scholar 

  46. Ovadia, Y. et al.: Can you trust your model’s uncertainty? evaluating predictive uncertainty under dataset shift. In: Proceedings of the Advances in Neural Information Processing Systems, vol. 32, pp. 13991–14002 (2019)

    Google Scholar 

  47. Roy, A.G., et al.: Does your dermatology classifier know what it doesn’t know? detecting the long-tail of unseen conditions. arXiv preprint. arXiv:2104.03829 (2021)

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

    Google Scholar 

  49. Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15, 1929–1958 (2014)

    MathSciNet  MATH  Google Scholar 

  50. Sun, Y., Guo, C., Li, Y.: React: out-of-distribution detection with rectified activations. In: Advances in Neural Information Processing Systems (2021)

    Google Scholar 

  51. Sun, Y., Ming, Y., Zhu, X., Li, Y.: Out-of-distribution detection with deep nearest neighbors. In: Proceedings of the International Conference on Machine Learning (2022)

    Google Scholar 

  52. Sun, Y., Ravi, S., Singh, V.: Adaptive activation thresholding: dynamic routing type behavior for interpretability in convolutional neural networks. In: Proceedings of the International Conference on Computer Vision (2019)

    Google Scholar 

  53. Sun, Y., Wang, X., Liu, Z., Miller, J., Efros, A., Hardt, M.: Test-time training with self-supervision for generalization under distribution shifts. In: Proceedings of the International Conference on Machine Learning. pp. 9229–9248. PMLR (2020)

    Google Scholar 

  54. Tack, J., Mo, S., Jeong, J., Shin, J.: Csi: novelty detection via contrastive learning on distributionally shifted instances. In: Advances in Neural Information Processing Systems (2020)

    Google Scholar 

  55. Van Amersfoort, J., Smith, L., Teh, Y.W., Gal, Y.: Uncertainty estimation using a single deep deterministic neural network. In: Proceedings of the International Conference on Machine Learning (2020)

    Google Scholar 

  56. Van Horn, G., et al.: The inaturalist species classification and detection dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8769–8778 (2018)

    Google Scholar 

  57. Wan, L., Zeiler, M.D., Zhang, S., LeCun, Y., Fergus, R.: Regularization of neural networks using dropconnect. In: Proceedings of the International Conference on Machine Learning, vol. 28, pp. 1058–1066 (2013)

    Google Scholar 

  58. Wang, H., Liu, W., Bocchieri, A., Li, Y.: Can multi-label classification networks know what they don’t know? Proceedings of the Advances in Neural Information Processing Systems (2021)

    Google Scholar 

  59. Wang, X., Peng, Y., Lu, L., Lu, Z., Bagheri, M., Summers, R.M.: Chestx-ray8: hospital-scale chest x-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2097–2106 (2017)

    Google Scholar 

  60. Wei, H., Xie, R., Cheng, H., Feng, L., An, B., Li, Y.: Mitigating neural network overconfidence with logit normalization. In: Proceedings of the International Conference on Machine Learning (2022)

    Google Scholar 

  61. Wong, E., Santurkar, S., Madry, A.: Leveraging sparse linear layers for debuggable deep networks. In: Proceedings of the International Conference on Machine Learning, pp. 11205–11216. PMLR (2021)

    Google Scholar 

  62. Xiao, J., Hays, J., Ehinger, K.A., Oliva, A., Torralba, A.: Sun database: large-scale scene recognition from abbey to zoo. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3485–3492. IEEE Computer Society (2010)

    Google Scholar 

  63. Xu, P., Ehinger, K.A., Zhang, Y., Finkelstein, A., Kulkarni, S.R., Xiao, J.: Turkergaze: crowdsourcing saliency with webcam based eye tracking. arXiv preprint. arXiv:1504.06755 (2015)

  64. Yang, J., et al.: Semantically coherent out-of-distribution detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 8301–8309 (2021)

    Google Scholar 

  65. Yu, F., Seff, A., Zhang, Y., Song, S., Funkhouser, T., Xiao, J.: Lsun: construction of a large-scale image dataset using deep learning with humans in the loop. arXiv preprint. arXiv:1506.03365 (2015)

  66. Zhang, C., Bengio, S., Hardt, M., Recht, B., Vinyals, O.: Understanding deep learning requires rethinking generalization. In: Proceedings of International Conference on Learning Representations

    Google Scholar 

  67. Zhou, B., Lapedriza, A., Khosla, A., Oliva, A., Torralba, A.: Places: a 10 million image database for scene recognition. In: IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 40, pp. 1452–1464. IEEE (2017)

    Google Scholar 

  68. Zhou, K., Liu, Z., Qiao, Y., Xiang, T., Loy, C.C.: Domain generalization: a survey (2021)

    Google Scholar 

Download references

Acknowledgement

Work was supported by funding from Wisconsin Alumni Research Foundation (WARF). The authors would also like to thank reviewers for the helpful feedback.

Author information

Authors and Affiliations

  1. Computer Scof Wisconsin-Madison, Madison, USA

    Yiyou Sun & Yixuan Li

Authors
  1. Yiyou Sun
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yixuan Li
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Yiyou Sun .

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 1080 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

Sun, Y., Li, Y. (2022). DICE: Leveraging Sparsification for 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 13684. Springer, Cham. https://doi.org/10.1007/978-3-031-20053-3_40

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-20053-3_40

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-20052-6

  • Online ISBN: 978-3-031-20053-3

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation