Abstract
Convolutional Neural Networks (CNN) are successfully being used for different computer vision tasks, from labeling cancerous cells in medical images to identify traffic signals in self-driving cars. Supervised CNN classify raw input data according to the patterns learned from an input training set. This set is typically obtained by manually labeling the image which can lead to uncertainties in the data. The level of expertise of the professionals labeling the training set sometimes varies widely or some of the images used may not be clear and are difficult to label. This leads to data sets with pictures labeled differently by different experts or uncertainty in the experts opinions.
These kind of errors on the training set do happen more frequently when the CNN task is to classify numerous labels with similar characteristics. For example, when labeling damages on civil infrastructures after an earthquake, there are more than two hundred different labels with some of them similar to each other and the experts labeling the sets frequently disagree on which one to use. In this paper, we use probabilistic analysis to evaluate both the likelihood of the labels in the training set (produced by the CNN) and the likelihood’s uncertainty. The uncertainty in the likelihood is represented by a probability density and represents a spreading (as it were) of the CNN’s likelihood estimate over a range of values dictated by the uncertainty in the truth set.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
At this stage of development, a triangular density function with a very narrow base has been used instead of an impulse.
- 2.
This is a restatement of Table 2 ordered by photo id.
- 3.
References
Patterson, B., Leone, G., Pantoja, M., Behrouzi, A.: Deep learning for automated image classification of seismic damage to built infrastructure. In: Proceedings of the 11th National Conference in Earthquake Engineering (2018)
Pantoja, M., Fabris, D., Behrouzi, A.: Deep learning basic overview concrete international magazine, September 2018
Tesla Crash Preliminary Report US department of transportation NHTSA PE 16–007
Sun, S., Chen, C., Carin, L.: Learning structured weight uncertainty in Bayesian neural networks. In: Proceedings of the 20th International Conference on Artificial Intelligence and Statistics (AISTATS) 2017, JMLR: W&CP, vol. 54, Fort Lauderdale (2017)
Kendall, A., Gal, Y.: What uncertainties do we need in Bayesian deep learning for computer vision NIPS (2017). https://arxiv.org/abs/1703.04977
Gal, Y., Ghahramani, Z.: Dropout as a Bayesian approximation: representing model uncertainty in deep learning. In: Proceedings of the 33rd International Conference on Machine Learning PMLR, vol. 48, pp. 1050–1059 (2016)
Deceus, T.: Handling imprecise and uncertain class labels in classification and clustering. Bayesian Deep Learning COST Action IC 0702 Working group C, Mallorca, 16 March 2009
Gal, Y.: What my Deep Learning model Doesnt know, 3 July 2015
David, H.: The Certainty-Factor Model, Encyclopedia of Artificial Intelligence. 2nd edn. pp. 131–138, Wiley, New York
Pearl, J.: Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. Morgan Kaufmann, San Mateo
Zadeh, L.A., Klir, G.J., Yuan, B. (eds.): Fuzzy Sets, Fuzzy Logic, and Fuzzy Systems Selected Papers. Advances in Fuzzy Systems Applications and Theory, vol 6. World Scientific
Knuth, D.E.: The Art of Computer Programming, vol. 2, Section 4.3.3, pp. 290–295
Press, W.H.: Numerical Recipes in C. Section 8.10, pp. 329–343 (1986)
Google Research Research Blog: AlphaGo: mastering the ancient game of Go with Machine Learning, 27 January 2016
Kendall, A., Badrinarayanan, V., Cipolla, R.: Bayesian SegNet: model uncertainty in deep convolutional encoder-decoder architectures for scene understanding, CoRR (2015). http://arxiv.org/abs/1511.02680
Weideman, H.: Quantifying uncertainty in neural networks. https://hjweide.github.io/quantifying-uncertainty-in-neural-networks
Avis, D., Fukuda, K.: A pivoting algorithm for convex hulls and vertex enumeration of arrangements and polyhedra. Discrete Comput. Geom. 8(3), 295–313 (1992)
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
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Pantoja, M., Kleinhenz, R., Fabris, D. (2020). Adding Probabilistic Certainty to Improve Performance of Convolutional Neural Networks. In: Crespo-Mariño, J., Meneses-Rojas, E. (eds) High Performance Computing. CARLA 2019. Communications in Computer and Information Science, vol 1087. Springer, Cham. https://doi.org/10.1007/978-3-030-41005-6_17
Download citation
DOI: https://doi.org/10.1007/978-3-030-41005-6_17
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-41004-9
Online ISBN: 978-3-030-41005-6
eBook Packages: Computer ScienceComputer Science (R0)