Abstract
This work focuses on improving uncertainty estimation in the field of object classification from RGB images and demonstrates its benefits in two robotic applications. We employ a Bayesian Neural Network (BNN), and evaluate two practical inference techniques to obtain better uncertainty estimates, namely Concrete Dropout (CDP) and Kronecker-factored Laplace Approximation (LAP). We show a performance increase using more reliable uncertainty estimates as unary potentials within a Conditional Random Field (CRF), which is able to incorporate contextual information as well. Furthermore, the obtained uncertainties are exploited to achieve domain adaptation in a semi-supervised manner, which requires less manual efforts in annotating data. We evaluate our approach on two public benchmark datasets that are relevant for robot perception tasks.
J. Feng and M. Durner—Equal contributions.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Gal, Y., Islam, R., Ghahramani, Z.: Deep Bayesian active learning with image data. In: Proceedings of the 34th International Conference on Machine Learning-Volume 70, pp. 1183–1192. JMLR. org (2017)
Blundell, C., Cornebise, J., Kavukcuoglu, K., Wierstra, D.: Weight uncertainty in neural network. In: International Conference on Machine Learning, pp. 1613–1622 (2015)
Osband, I., Blundell, C., Pritzel, A., Van Roy, B.: Deep exploration via bootstrapped DQN. In: Advances in Neural Information Processing Systems, pp. 4026–4034 (2016)
Gal, Y., McAllister, R., Rasmussen, C.E.: Improving PILCO with Bayesian neural network dynamics models. In: Data-Efficient Machine Learning workshop, ICML (2016)
Grimmett, H., Triebel, R., Paul, R., Posner, I.: Introspective classification for robot perception. Int. J. Robot. Res. (IJRR) 35(7), 743–762 (2016)
Hendrycks, D., Gimpel, K.: A baseline for detecting misclassified and out-of-distribution examples in neural networks. In: 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, 24–26 April 2017, Conference Track Proceedings (2017). https://openreview.net/forum?id=Hkg4TI9xl
Kurakin, A., Goodfellow, I., Bengio, S.: Adversarial machine learning at scale. ar**v preprint ar**v:1611.01236 (2016)
Balan, A.K., Rathod, V., Murphy, K.P., Welling, M.: Bayesian dark knowledge. In: Advances in Neural Information Processing Systems, pp. 3438–3446 (2015)
Gal, Y., Ghahramani, Z.: Dropout as a Bayesian approximation: representing model uncertainty in deep learning. In: International Conference on Machine Learning, pp. 1050–1059 (2016)
Louizos, C., Welling, M.: Structured and efficient variational deep learning with matrix gaussian posteriors. In: International Conference on Machine Learning, pp. 1708–1716 (2016)
Gal, Y., Hron, J., Kendall, A.: Concrete dropout. In: Advances in Neural Information Processing Systems, pp. 3581–3590 (2017)
Sun, S., Chen, C., Carin, L.: Learning structured weight uncertainty in Bayesian neural networks. In: Artificial Intelligence and Statistics, pp. 1283–1292 (2017)
Louizos, C., Welling, M.: Multiplicative normalizing flows for variational Bayesian neural networks. In: Proceedings of the 34th International Conference on Machine Learning, vol. 70, pp. 2218–2227. JMLR. org (2017)
Ritter, H., Botev, A., Barber, D.: A scalable Laplace approximation for neural networks. In: International Conference on Learning Representations (2018). https://openreview.net/forum?id=Skdvd2xAZ
Wang, K., Vicol, P., Lucas, J., Gu, L., Grosse, R.B., Zemel, R.S.: Adversarial distillation of Bayesian neural network posteriors. In: Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholmsmässan, Stockholm, Sweden, 10–15 July 2018, pp. 5177–5186 (2018)
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)
Koller, D., Friedman, N.: Probabilistic Graphical Models: Principles and Techniques. MIR Press, Cambridge (2009)
Tompson, J.J., Jain, A., LeCun, Y., Bregler, C.: Joint training of a convolutional network and a graphical model for human pose estimation. In: Advances in Neural Information Processing Systems, pp. 1799–1807 (2014)
Liu, F., Shen, C., Lin, G.: Deep convolutional neural fields for depth estimation from a single image. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5162–5170 (2015)
Wang, H., Yeung, D.Y.: Towards Bayesian deep learning: a survey. ar**v preprint ar**v:1604.01662 (2016)
Johnson, M., Duvenaud, D.K., Wiltschko, A., Adams, R.P., Datta, S.R.: Composing graphical models with neural networks for structured representations and fast inference. In: Advances in Neural Information Processing Systems, pp. 2946–2954 (2016)
Kolesnikov, A., Zhai, X., Beyer, L.: Revisiting self-supervised visual representation learning. ar**v preprint ar**v:1901.09005 (2019)
Tang, K., Ramanathan, V., Fei-Fei, L., Koller, D.: Shifting weights: adapting object detectors from image to video. In: Advances in Neural Information Processing Systems, pp. 638–646 (2012)
Zou, Y., Yu, Z., Vijaya Kumar, B., Wang, J.: Unsupervised domain adaptation for semantic segmentation via class-balanced self-training. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 289–305 (2018)
Xu, J., **ao, L., Lopez, A.M.: Self-supervised domain adaptation for computer vision tasks. ar**v preprint ar**v:1907.10915 (2019)
Wang, K., Zhang, D., Li, Y., Zhang, R., Lin, L.: Cost-effective active learning for deep image classification. IEEE Trans. Circuits Syst. Video Technol. 27(12), 2591–2600 (2016)
Lin, L., Wang, K., Meng, D., Zuo, W., Zhang, L.: Active self-paced learning for cost-effective and progressive face identification. IEEE Trans. Pattern Anal. Mach. Intell. 40(1), 7–19 (2017)
MacKay, D.J.: A practical Bayesian framework for backpropagation networks. Neural Comput. 4(3), 448–472 (1992)
Neal, R.M.: Bayesian Learning For Neural Networks. LNS, vol. 118. Springer Science & Business Media, New York (2012). https://doi.org/10.1007/978-1-4612-0745-0
Graves, A.: Practical variational inference for neural networks. In: Advances in Neural Information Processing Systems, pp. 2348–2356 (2011)
Liu, F., Lin, G., Shen, C.: CRF learning with CNN features for image segmentation. Pattern Recogn. 48(10), 2983–2992 (2015)
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(1), 1929–1958 (2014)
Gal, Y.: Uncertainty in deep learning. Ph.D. thesis, University of Cambridge (2016)
Maddison, C.J., Mnih, A., Teh, Y.W.: The concrete distribution: a continuous relaxation of discrete random variables. ar**v preprint ar**v:1611.00712 (2016)
Martens, J., Grosse, R.: Optimizing neural networks with Kronecker-factored approximate curvature. In: International Conference on Machine Learning, pp. 2408–2417 (2015)
Gupta, A., Nagar, D.: Matrix Variate Distributions, vol. 104. CRC Press, Boca Raton (1999)
Ruiz-Sarmiento, J.R., Galindo, C., González-Jiménez, J.: UPGMpp: a software library for contextual object recognition. In: 3rd Workshop on Recognition and Action for Scene Understanding (REACTS) (2015)
Lai, K., Bo, L., Ren, X., Fox, D.: A large-scale hierarchical multi-view RGB-D object dataset. In: 2011 IEEE International Conference on Robotics and Automation, pp. 1817–1824. IEEE (2011)
Hodaň, T., Haluza, P., Obdržálek, Š., Matas, J., Lourakis, M., Zabulis, X.: T-LESS: an RGB-D dataset for 6D pose estimation of texture-less objects. In: IEEE Winter Conference on Applications of Computer Vision (WACV) (2017)
Guo, C., Pleiss, G., Sun, Y., Weinberger, K.Q.: On calibration of modern neural networks. In: Proceedings of the 34th International Conference on Machine Learning-Volume 70, pp. 1321–1330. JMLR. org (2017)
Gneiting, T., Balabdaoui, F., Raftery, A.E.: Probabilistic forecasts, calibration and sharpness. J. R. Stat. Soc. Ser. B (Stat. Methodol.) 69(2), 243–268 (2007)
Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. 115(3), 211–252 (2015)
Acknowledgments
This work was partially funded by the Big Data Interdisciplinary Project of DLR e.V. under the project number 2464047. Jianxiang Feng is supported by the Munich School for Data Science (MUDS) and Rudolph Triebel is a member of MUDS.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Feng, J., Durner, M., Márton, ZC., Bálint-Benczédi, F., Triebel, R. (2022). Introspective Robot Perception Using Smoothed Predictions from Bayesian Neural Networks. In: Asfour, T., Yoshida, E., Park, J., Christensen, H., Khatib, O. (eds) Robotics Research. ISRR 2019. Springer Proceedings in Advanced Robotics, vol 20. Springer, Cham. https://doi.org/10.1007/978-3-030-95459-8_40
Download citation
DOI: https://doi.org/10.1007/978-3-030-95459-8_40
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-95458-1
Online ISBN: 978-3-030-95459-8
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)