Abstract
DNNs have been excelling on many computer vision tasks, achieving many milestones and are continuing to prove their validity. It is important for DNNs to express their uncertainties to be taken into account for the whole application output, whilst maintaining their performance. The intermediate layer variational inference has been a promising approach to estimate uncertainty in real-time beating state-of-the-art approaches. In this work, we propose an enhancement of the intermediate layer variational inference by adding Dirichlet distribution to the network architecture. This improves, on one hand, the uncertainty estimation reliability and on the other hand can detect out-of-distribution samples. Results show that with the addition of Dirichlet distributions the DNN is able to maintain its segmentation performance whilst boosting its uncertainty estimation capabilities.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Kermany, D.S., et al.: Identifying medical diagnoses and treatable diseases by image-based deep learning. Cell 172(5), 1122–1131 (2018)
Alexander Selvikvåg Lundervold and Arvid Lundervold: An overview of deep learning in medical imaging focusing on MRI. Zeitschrift für Medizinische Physik 29(2), 102–127 (2019)
Zhu, M., Wang, X., Wang, Y.: Human-like autonomous car-following model with deep reinforcement learning. Transp. Res. part C: Emerg. Technol. 97, 348–368 (2018)
Wang, X., Jiang, R., Li, L., Lin, Y., Zheng, X., Wang, F.-Y.: Capturing car-following behaviors by deep learning. IEEE Trans. Intell. Transp. Syst. 19(3), 910–920 (2017)
Wu, X., et al.: Sparse fuse dense: Towards high quality 3D detection with depth completion. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5418–5427, (2022)
Wang, C.-H., Chen, H.-W., Fu, L-C.: VPFNet: voxel-pixel fusion network for multi-class 3D object detection. ar**v preprint ar**v:2111.00966 (2021)
Aradi, S.: Survey of deep reinforcement learning for motion planning of autonomous vehicles. IEEE Trans. Intell. Transp. Syst. 23, 740–759 (2020)
Liu, W., et al.: SSD: single shot MultiBox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21–37. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46448-0_2
Redmon, J., Farhadi, A.: YOLOv3: an incremental improvement. ar**v preprint ar**v:1804.02767. (2018)
Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 801–818 (2018)
Wang, J., et al.: Deep high-resolution representation learning for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 43(10), 3349–3364 (2020)
Willers, O., Sudholt, S., Raafatnia, S., Abrecht, S.: Safety concerns and mitigation approaches regarding the use of deep learning in safety-critical perception tasks. In: Casimiro, A., Ortmeier, F., Schoitsch, E., Bitsch, F., Ferreira, P. (eds.) SAFECOMP 2020. LNCS, vol. 12235, pp. 336–350. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-55583-2_25
Akhtar, N., Mian, A.: Threat of adversarial attacks on deep learning in computer vision: a survey. IEEE Access 6, 14410–14430 (2018)
Ozdag, M.: Adversarial attacks and defenses against deep neural networks: a survey. Procedia Comput. Sci. 140, 152–161 (2018)
Smuha, N.A.: The EU approach to ethics guidelines for trustworthy artificial intelligence. Comput. Law Rev. Int. 20(4), 97–106 (2019)
Dietterich, T.G.: Steps toward robust artificial intelligence. Ai Mag. 38(3), 3–24 (2017)
Kendall, A.: Geometry and uncertainty in deep learning for computer vision. PhD thesis, University of Cambridge, UK (2019)
Gal, Y.: Uncertainty in deep learning (2016)
Abdar, M., et al.: A review of uncertainty quantification in deep learning: techniques, applications and challenges. Inf. Fusion 76, 243–297 (2021)
Gawlikowski, J., et al.: A survey of uncertainty in deep neural networks. ar**v preprint ar**v:2107.03342 (2021)
Hammam, A., Ghobadi, S.E., Bonarens, F., Stiller, C.: Real-time uncertainty estimation based on intermediate layer variational inference. In: Computer Science in Cars Symposium, pp. 1–9 (2021)
MacKay, D.J.C.: A practical bayesian framework for backpropagation networks. Neural Comput. 4(3), 448–472 (1992)
Graves, A.: Practical variational inference for neural networks. In: Advances in Neural Information Processing Systems. 24 (2011)
Blundell, C., Cornebise, J., Kavukcuoglu, K., Wierstra, D.: Weight uncertainty in neural network. In: International Conference on Machine Learning, pp. 1613–1622. PMLR (2015)
Mukhoti, J., Gal, Y.: Evaluating bayesian deep learning methods for semantic segmentation. ar**v preprint ar**v:1811.12709 (2018)
Gustafsson, F.K., Danelljan, M., Schon, T.B.: Evaluating scalable bayesian deep learning methods for robust computer vision. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 318–319 (2020)
Gal, Y., Ghahramani, Z.: Dropout as a bayesian approximation: representing model uncertainty in deep learning. In: International Conference on Machine Learning, pp. 1050–1059. PMLR (2016)
Lakshminarayanan, B., Pritzel, A., Blundell, C.: Simple and scalable predictive uncertainty estimation using deep ensembles. ar**v preprint ar**v:1612.01474 (2016)
Malinin, A., Gales, M.: Predictive uncertainty estimation via prior networks. In: Advances in Neural Information Processing Systems. 31 (2018)
Sensoy, M., Kaplan, L., Kandemir, M.: Evidential deep learning to quantify classification uncertainty. In: Advances in Neural Information Processing Systems 31 (2018)
Nandy, J., Hsu, W., Lee, M.L.: Towards maximizing the representation gap between in-domain & out-of-distribution examples. Adv. Neural Inf. Process. Syst. 33, 9239–9250 (2020)
Malinin, A., Gales, M.: Reverse KL-divergence training of prior networks: Improved uncertainty and adversarial robustness. In: Advances in Neural Information Processing Systems. 32 (2019)
Charpentier, B., Zügner, D., Günnemann, S.: Posterior network: uncertainty estimation without OOD samples via density-based pseudo-counts. Adv. Neural Inf. Process. Syst. 33, 1356–1367 (2020)
Drummond, N., Shearer, R.: The open world assumption. In eSI Workshop: The Closed World of Databases meets the Open World of the Semantic Web, vol. 15, pp. 1 (2006)
Hendrycks, D., Gimpel, K.: A baseline for detecting misclassified and out-of-distribution examples in neural networks. ar**v preprint ar**v:1610.02136 (2016)
Yang, J., Zhou, K., Li, Y., Liu, Z.: Generalized out-of-distribution detection: a survey. ar**v preprint ar**v:2110.11334 (2021)
Nitsch, J., et al.: Out-of-distribution detection for automotive perception. In: 2021 IEEE International Intelligent Transportation Systems Conference (ITSC), pp. 2938–2943. IEEE (2021)
Filos, A., Tigkas, P., McAllister, R., Rhinehart, N., Levine, S., Gal, Y.: Can autonomous vehicles identify, recover from, and adapt to distribution shifts? In: International Conference on Machine Learning, pp. 3145–3153. PMLR (2020)
Chan, R., et al.: SegmentMeifYouCan: a benchmark for anomaly segmentation. ar**v preprint ar**v:2104.14812 (2021)
Vernekar, S., Gaurav, A., Abdelzad, V., Denouden, T., Salay, R., Czarnecki, K.: Out-of-distribution detection in classifiers via generation. ar**v preprint ar**v:1910.04241 (2019)
Zhou, D.-W., Ye, H.-J., Zhan, D.-C.: Learning placeholders for open-set recognition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4401–4410 (2021)
Hendrycks, D., Mazeika, M., Dietterich, T.: Deep anomaly detection with outlier exposure. ar**v preprint ar**v:1812.04606 (2018)
Jourdan, N., Rehder, E., Franke, U.: Identification of uncertainty in artificial neural networks. In: Proceedings of the 13th Uni-DAS eV Workshop Fahrerassistenz und automatisiertes Fahren. vol. 2, pp. 12 (2020)
Vyas, A., Jammalamadaka, N., Zhu, X., Das, D., Kaul, B., Willke, T.L.: Out-of-distribution detection using an ensemble of self supervised leave-out classifiers. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 550–564 (2018)
Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3213–3223 (2016)
Henne, M., Schwaiger, A., Roscher, K., Weiss, G.: Benchmarking uncertainty estimation methods for deep learning with safety-related metrics. In: SafeAI@ AAAI, pp. 83–90 (2020)
Liang, S., Li, Y., Srikant, R.: Enhancing the reliability of out-of-distribution image detection in neural networks. ar**v preprint ar**v:1706.02690 (2017)
Neumann, L., Zisserman, A., Vedaldi.: Relaxed softmax: efficient confidence auto-calibration for safe pedestrian detection (2018)
Naeini, M.P., Cooper, G., Hauskrecht, M.: Obtaining well calibrated probabilities using bayesian binning. In: Twenty-Ninth AAAI Conference on Artificial Intelligence (2015)
Acknowledgments
The research leading to these results is partly funded by the German Federal Ministry for Economic Affairs and Climate Action within the project “Methoden und Maßnahmen zur Absicherung von KI basierten Wahrnehmungsfunktionen für das automatisierte Fahren (KI-Absicherung)”. The authors would like to thank the consortium for the successful cooperation.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Hammam, A., Bonarens, F., Ghobadi, S.E., Stiller, C. (2023). Towards Improved Intermediate Layer Variational Inference for Uncertainty Estimation. In: Karlinsky, L., Michaeli, T., Nishino, K. (eds) Computer Vision – ECCV 2022 Workshops. ECCV 2022. Lecture Notes in Computer Science, vol 13805. Springer, Cham. https://doi.org/10.1007/978-3-031-25072-9_36
Download citation
DOI: https://doi.org/10.1007/978-3-031-25072-9_36
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-25071-2
Online ISBN: 978-3-031-25072-9
eBook Packages: Computer ScienceComputer Science (R0)