Skip to main content
SpringerLink
Log in

Latent Discriminant Deterministic Uncertainty

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

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 13672))

Included in the following conference series:

Abstract

Predictive uncertainty estimation is essential for deploying Deep Neural Networks in real-world autonomous systems. However, most successful approaches are computationally intensive. In this work, we attempt to address these challenges in the context of autonomous driving perception tasks. Recently proposed Deterministic Uncertainty Methods (DUM) can only partially meet such requirements as their scalability to complex computer vision tasks is not obvious. In this work we advance a scalable and effective DUM for high-resolution semantic segmentation, that relaxes the Lipschitz constraint typically hindering practicality of such architectures. We learn a discriminant latent space by leveraging a distinction maximization layer over an arbitrarily-sized set of trainable prototypes. Our approach achieves competitive results over Deep Ensembles, the state of the art for uncertainty prediction, on image classification, segmentation and monocular depth estimation tasks. Our code is available at https://github.com/ENSTA-U2IS/LDU.

G. Franchi and Franchi X. Yu—Equal contribution.

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

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

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

Similar content being viewed by others

References

  1. Aggarwal, C.C., Hinneburg, A., Keim, D.A.: On the surprising behavior of distance metrics in high dimensional space. In: Van den Bussche, J., Vianu, V. (eds.) ICDT 2001. LNCS, vol. 1973, pp. 420–434. Springer, Heidelberg (2001). https://doi.org/10.1007/3-540-44503-X_27

    Chapter  Google Scholar 

  2. Alemi, A.A., Fischer, I., Dillon, J.V.: Uncertainty in the variational information bottleneck. In: UAI (2018)

    Google Scholar 

  3. van Amersfoort, J., Smith, L., Jesson, A., Key, O., Gal, Y.: Improving deterministic uncertainty estimation in deep learning for classification and regression. arXiv preprint arXiv:2102.11409 (2021)

  4. Arjovsky, M., Chintala, S., Bottou, L.: Wasserstein generative adversarial networks. In: ICLR (2017)

    Google Scholar 

  5. Asai, A., Ikami, D., Aizawa, K.: Multi-task learning based on separable formulation of depth estimation and its uncertainty. In: CVPR Workshops (2019)

    Google Scholar 

  6. Assent, I.: Clustering high dimensional data. KDD (2012)

    Google Scholar 

  7. Behrmann, J., Grathwohl, W., Chen, R.T., Duvenaud, D., Jacobsen, J.H.: Invertible residual networks. In: ICML (2019)

    Google Scholar 

  8. Besnier, V., Bursuc, A., Picard, D., Briot, A.: Triggering failures: out-of-distribution detection by learning from local adversarial attacks in semantic segmentation. In: ICCV (2021)

    Google Scholar 

  9. Bhat, S.F., Alhashim, I., Wonka, P.: AdaBins: depth estimation using adaptive bins. In: CVPR (2021)

    Google Scholar 

  10. Blundell, C., Cornebise, J., Kavukcuoglu, K., Wierstra, D.: Weight uncertainty in neural network. In: ICML (2015)

    Google Scholar 

  11. Boucheron, S., Lugosi, G., Massart, P.: Concentration Inequalities: A Nonasymptotic Theory of Independence. Oxford University Press, Oxford (2013)

    Google Scholar 

  12. Cao, Z., Hidalgo Martinez, G., Simon, T., Wei, S., Sheikh, Y.A.: OpenPose: realtime multi-person 2D pose estimation using part affinity fields. TPAMI (2019)

    Google Scholar 

  13. Chen, G., et al.: Learning open set network with discriminative reciprocal points. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12348, pp. 507–522. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58580-8_30

    Chapter  Google Scholar 

  14. Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 833–851. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01234-2_49

    Chapter  Google Scholar 

  15. Corbière, C., Thome, N., Bar-Hen, A., Cord, M., Pérez, P.: Addressing failure prediction by learning model confidence. In: NeurIPS (2019)

    Google Scholar 

  16. Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: CVPR (2016)

    Google Scholar 

  17. Der Kiureghian, A., Ditlevsen, O.: Aleatory or epistemic? Does it matter? Structural safety (2009)

    Google Scholar 

  18. Dijk, T.v., Croon, G.d.: How do neural networks see depth in single images? In: ICCV (2019)

    Google Scholar 

  19. Du, X., Wang, Z., Cai, M., Li, Y.: VOS: learning what you don’t know by virtual outlier synthesis. In: ICLR (2022)

    Google Scholar 

  20. Dusenberry, M., et al.: Efficient and scalable Bayesian neural nets with rank-1 factors. In: ICML (2020)

    Google Scholar 

  21. Eigen, D., Puhrsch, C., Fergus, R.: Depth map prediction from a single image using a multi-scale deep network. In: NeurIPS (2014)

    Google Scholar 

  22. Everingham, M., et al.: The Pascal visual object classes challenge: a retrospective. Int. J. Comput. Vis. 111(1), 98–136 (2014). https://doi.org/10.1007/s11263-014-0733-5

    Article  Google Scholar 

  23. Fort, S., Hu, H., Lakshminarayanan, B.: Deep ensembles: a loss landscape perspective. arXiv preprint arXiv:1912.02757 (2019)

  24. Franchi, G., Belkhir, N., Ha, M.L., Hu, Y., Bursuc, A., Blanz, V., Yao, A.: Robust semantic segmentation with superpixel-mix. In: BMVC (2021)

    Google Scholar 

  25. Franchi, G., Bursuc, A., Aldea, E., Dubuisson, S., Bloch, I.: TRADI: tracking deep neural network weight distributions. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12362, pp. 105–121. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58520-4_7

    Chapter  Google Scholar 

  26. Franchi, G., et al.: MUAD: multiple uncertainties for autonomous driving benchmark for multiple uncertainty types and tasks. arXiv preprint arXiv:2203.01437 (2022)

  27. Gal, Y., Ghahramani, Z.: Dropout as a Bayesian approximation: representing model uncertainty in deep learning. In: ICML (2016)

    Google Scholar 

  28. Gidaris, S., Komodakis, N.: Dynamic few-shot visual learning without forgetting. In: CVPR (2018)

    Google Scholar 

  29. Gong, D., et al.: Memorizing normality to detect anomaly: memory-augmented deep autoencoder for unsupervised anomaly detection. In: ICCV (2019)

    Google Scholar 

  30. Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., Courville, A.: Improved training of Wasserstein GANs. In: NeurIPS (2017)

    Google Scholar 

  31. Guo, C., Pleiss, G., Sun, Y., Weinberger, K.Q.: On calibration of modern neural networks. In: ICML (2017)

    Google Scholar 

  32. Gustafsson, F.K., Danelljan, M., Schon, T.B.: Evaluating scalable Bayesian deep learning methods for robust computer vision. In: CVPR Workshops (2020)

    Google Scholar 

  33. He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)

    Google Scholar 

  34. Hendrycks, D., Basart, S., Mazeika, M., Mostajabi, M., Steinhardt, J., Song, D.: A benchmark for anomaly segmentation. arXiv preprint arXiv:1911.11132 (2019)

  35. Hendrycks, D., Dietterich, T.: Benchmarking neural network robustness to common corruptions and perturbations. In: ICLR (2019)

    Google Scholar 

  36. Hendrycks, D., Gimpel, K.: A baseline for detecting misclassified and out-of-distribution examples in neural networks. In: ICLR (2017)

    Google Scholar 

  37. Hernández-Lobato, J.M., Adams, R.: Probabilistic backpropagation for scalable learning of Bayesian neural networks. In: ICML (2015)

    Google Scholar 

  38. Hu, S., Pezzotti, N., Welling, M.: Learning to predict error for MRI reconstruction. In: de Bruijne, M., et al. (eds.) MICCAI 2021. LNCS, vol. 12903, pp. 604–613. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-87199-4_57

    Chapter  Google Scholar 

  39. Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: CVPR (2017)

    Google Scholar 

  40. Ilg, E., et al.: Uncertainty estimates and multi-hypotheses networks for optical flow. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 677–693. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01234-2_40

    Chapter  Google Scholar 

  41. Kamann, C., Rother, C.: Benchmarking the robustness of semantic segmentation models with respect to common corruptions. IJCV (2021)

    Google Scholar 

  42. Kendall, A., Badrinarayanan, V., Cipolla, R.: Bayesian SegNet: model uncertainty in deep convolutional encoder-decoder architectures for scene understanding. arXiv preprint arXiv:1511.02680 (2015)

  43. Kendall, A., Gal, Y.: What uncertainties do we need in Bayesian deep learning for computer vision? In: NeurIPS (2017)

    Google Scholar 

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

    Google Scholar 

  45. Lakshminarayanan, B., Pritzel, A., Blundell, C.: Simple and scalable predictive uncertainty estimation using deep ensembles. In: NeurIPS (2017)

    Google Scholar 

  46. Lee, J.H., Han, M.K., Ko, D.W., Suh, I.H.: From big to small: multi-scale local planar guidance for monocular depth estimation. arXiv preprint arXiv:1907.10326 (2019)

  47. Liu, C.L., Nakagawa, M.: Evaluation of prototype learning algorithms for nearest-neighbor classifier in application to handwritten character recognition. Pattern Recognit. 34, 601–615

    Google Scholar 

  48. Liu, J.Z., Lin, Z., Padhy, S., Tran, D., Bedrax-Weiss, T., Lakshminarayanan, B.: Simple and principled uncertainty estimation with deterministic deep learning via distance awareness. In: NeurIPS (2020)

    Google Scholar 

  49. Macêdo, D., Ren, T.I., Zanchettin, C., Oliveira, A.L., Ludermir, T.: Entropic out-of-distribution detection. In: IJCNN (2021)

    Google Scholar 

  50. Macêdo, D., Zanchettin, C., Ludermir, T.: Distinction maximization loss: efficiently improving classification accuracy, uncertainty estimation, and out-of-distribution detection simply replacing the loss and calibrating. arXiv preprint arXiv:2205.05874 (2022)

  51. Malinin, A., Gales, M.: Predictive uncertainty estimation via prior networks (2018)

    Google Scholar 

  52. Malinin, A., Mlodozeniec, B., Gales, M.: Ensemble distribution distillation. In: ICLR (2020)

    Google Scholar 

  53. Mandelbaum, A., Weinshall, D.: Distance-based confidence score for neural network classifiers. arXiv preprint arXiv:1709.09844 (2017)

  54. Mi, L., Wang, H., Tian, Y., Shavit, N.: Training-free uncertainty estimation for dense regression: Sensitivity as a surrogate. In: AAAI (2022)

    Google Scholar 

  55. Miyato, T., Kataoka, T., Koyama, M., Yoshida, Y.: Spectral normalization for generative adversarial networks. In: ICLR (2018)

    Google Scholar 

  56. Mukhoti, J., Kirsch, A., van Amersfoort, J., Torr, P.H., Gal, Y.: Deterministic neural networks with appropriate inductive biases capture epistemic and aleatoric uncertainty. In: ICML Workshops (2021)

    Google Scholar 

  57. Mukhoti, J., Kulharia, V., Sanyal, A., Golodetz, S., Torr, P.H., Dokania, P.K.: Calibrating deep neural networks using focal loss. In: NeurIPS (2020)

    Google Scholar 

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

    Google Scholar 

  59. Nix, D., Weigend, A.: Estimating the mean and variance of the target probability distribution. In: ICNN (1994)

    Google Scholar 

  60. Ovadia, Y., et al.: Can you trust your model’s uncertainty? Evaluating predictive uncertainty under dataset shift. In: NeurIPS (2019)

    Google Scholar 

  61. Padhy, S., Nado, Z., Ren, J., Liu, J., Snoek, J., Lakshminarayanan, B.: Revisiting one-vs-all classifiers for predictive uncertainty and out-of-distribution detection in neural networks. In: ICML Workshops (2020)

    Google Scholar 

  62. Pinto, F., Yang, H., Lim, S.N., Torr, P., Dokania, P.K.: Mix-MaxEnt: improving accuracy and uncertainty estimates of deterministic neural networks. In: NeurIPS Workshops (2021)

    Google Scholar 

  63. Poggi, M., Aleotti, F., Tosi, F., Mattoccia, S.: On the uncertainty of self-supervised monocular depth estimation. In: CVPR (2020)

    Google Scholar 

  64. Postels, J., et al.: The hidden uncertainty in a neural networks activations. In: ICML (2021)

    Google Scholar 

  65. Postels, J., Segu, M., Sun, T., Van Gool, L., Yu, F., Tombari, F.: On the practicality of deterministic epistemic uncertainty. arXiv preprint arXiv:2107.00649 (2021)

  66. Qi, H., Brown, M., Lowe, D.G.: Low-shot learning with imprinted weights. In: CVPR (2018)

    Google Scholar 

  67. Razavi, A., Van den Oord, A., Vinyals, O.: Generating diverse high-fidelity images with VQ-VAE-2. In: NeurIPS (2019)

    Google Scholar 

  68. Rebut, J., Bursuc, A., Pérez, P.: StyleLess layer: improving robustness for real-world driving. In: IROS (2021)

    Google Scholar 

  69. Rogez, G., Weinzaepfel, P., Schmid, C.: LCR-Net++: multi-person 2D and 3D pose detection in natural images. TPAMI (2019)

    Google Scholar 

  70. Snell, J., Swersky, K., Zemel, R.S.: Prototypical networks for few-shot learning. In: NeurIPS (2017)

    Google Scholar 

  71. Sun, D., Yang, X., Liu, M.Y., Kautz, J.: PWC-Net: CNNs for optical flow using pyramid, warping, and cost volume. In: CVPR (2018)

    Google Scholar 

  72. Teed, Z., Deng, J.: RAFT: recurrent all-pairs field transforms for optical flow. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12347, pp. 402–419. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58536-5_24

    Chapter  Google Scholar 

  73. Uhrig, J., Schneider, N., Schneider, L., Franke, U., Brox, T., Geiger, A.: Sparsity invariant CNNs. In: 3DV (2017)

    Google Scholar 

  74. Van Amersfoort, J., Smith, L., Teh, Y.W., Gal, Y.: Uncertainty estimation using a single deep deterministic neural network. In: ICML (2020)

    Google Scholar 

  75. Van Den Oord, A., Vinyals, O., et al.: Neural discrete representation learning. In: NeurIPS (2017)

    Google Scholar 

  76. Wen, Y., Zhang, K., Li, Z., Qiao, Yu.: A discriminative feature learning approach for deep face recognition. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9911, pp. 499–515. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46478-7_31

    Chapter  Google Scholar 

  77. Wen, Y., Tran, D., Ba, J.: BatchEnsemble: an alternative approach to efficient ensemble and lifelong learning. In: ICLR (2020)

    Google Scholar 

  78. Wilson, A.G., Izmailov, P.: Bayesian deep learning and a probabilistic perspective of generalization. arXiv preprint arXiv:2002.08791 (2020)

  79. Wu, M., Goodman, N.: A simple framework for uncertainty in contrastive learning. arXiv preprint arXiv:2010.02038 (2020)

  80. Yang, H.M., Zhang, X.Y., Yin, F., Liu, C.L.: Robust classification with convolutional prototype learning. In: CVPR (2018)

    Google Scholar 

  81. Yu, X., Franchi, G., Aldea, E.: SLURP: Side learning uncertainty for regression problems. In: BMVC (2021)

    Google Scholar 

  82. Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. In: CVPR (2017)

    Google Scholar 

Download references

Acknowledgements

This work was performed using HPC resources from GENCI-IDRIS (Grant 2020-AD011011970) and (Grant 2021-AD011011970R1) and Saclay-IA computing platform.

Author information

Authors and Affiliations

  1. U2IS, ENSTA Paris, Institut polytechnique de Paris, Palaiseau, France

    Gianni Franchi, Xuanlong Yu & David Filliat

  2. SATIE, Paris-Saclay University, Gif-sur-Yvette, France

    Xuanlong Yu & Emanuel Aldea

  3. valeo.ai, Paris, France

    Andrei Bursuc

  4. CNRS, LIS, Aix Marseille University, Marseille, France

    Severine Dubuisson

Authors
  1. Gianni Franchi
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Xuanlong Yu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Andrei Bursuc
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Emanuel Aldea
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Severine Dubuisson
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. David Filliat
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Gianni Franchi .

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 4665 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

Franchi, G., Yu, X., Bursuc, A., Aldea, E., Dubuisson, S., Filliat, D. (2022). Latent Discriminant Deterministic Uncertainty. 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 13672. Springer, Cham. https://doi.org/10.1007/978-3-031-19775-8_15

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-19775-8_15

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-19774-1

  • Online ISBN: 978-3-031-19775-8

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation