Abstract
As a step in a Dynamic Data-Driven Applications Systems (DDDAS) method to characterize the background in a vehicle tracking problem, we extend the application of deep learning to a hyperspectral dataset (the AeroRIT dataset) to evaluating network uncertainty. Expressing uncertainty information is crucial for evaluating what additional information is needed in the DDDAS algorithm and where more resources are required. Hyperspectral signatures tend to be very noisy, when captured from an aerial flight and a slight shift in the atmospheric conditions can alter the signals significantly, which in turn may affect the trained network’s classifications. In this work, we apply Deep Ensembles, Monte Carlo Dropout and Batch Ensembles and study their effects with respect to achieving robust pixel-level identifications by expressing the uncertainty within the trained networks on the task of semantic segmentation. We modify the U-Net-m architecture from the AeroRIT paper to account for the frameworks and present our results as a step towards accounting for sensitive changes in hyperspectral signals.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Badrinarayanan, V., Kendall, A., Cipolla, R.: Segnet: A deep convolutional encoder-decoder architecture for image segmentation. arXiv preprint arXiv:1511.00561 (2015)
Blundell, C., Cornebise, J., Kavukcuoglu, K., Wierstra, D.: Weight uncertainty in neural networks. arXiv preprint arXiv:1505.05424 (2015)
Cobb, A.D., et al.: An ensemble of bayesian neural networks for exoplanetary atmospheric retrieval. Astronomical J. 158(1), 33 (2019)
Darema, F.: Dynamic data driven applications systems: a new paradigm for application simulations and measurements. In: Bubak, M., van Albada, G.D., Sloot, P.M.A., Dongarra, J. (eds.) ICCS 2004. LNCS, vol. 3038, pp. 662–669. Springer, Heidelberg (2004). https://doi.org/10.1007/978-3-540-24688-6_86
Der Kiureghian, A., Ditlevsen, O.: Aleatory or epistemic? does it matter? Structural Safety 31(2), 105–112 (2009)
Fletcher, S., Lickley, M., Strzepek, K.: Learning about climate change uncertainty enables flexible water infrastructure planning. Nat. Commun. 10(1), 1–11 (2019)
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)
Huang, G., Li, Y., Pleiss, G., Liu, Z., Hopcroft, J.E., Weinberger, K.Q.: Snapshot ensembles: Train 1, get m for free. arXiv preprint arXiv:1704.00109 (2017)
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)
Kendall, A., Gal, Y.: What uncertainties do we need in bayesian deep learning for computer vision? In: Advances in Neural Information Processing Systems, pp. 5574–5584 (2017)
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)
Loshchilov, I., Hutter, F.: Sgdr: Stochastic gradient descent with warm restarts. arXiv preprint arXiv:1608.03983 (2016)
Rangnekar, A., Mokashi, N., Ientilucci, E.J., Kanan, C., Hoffman, M.J.: Aerorit: a new scene for hyperspectral image analysis. IEEE Trans. Geosci. Remote Sens. 1, 1–9 (2020)
Rao, V., Sandu, A.: A posteriori error estimates for dddas inference problems. Procedia Comput. Sci. 29, 1256–1265 (2014)
Ritter, H., Botev, A., Barber, D.: A scalable laplace approximation for neural networks. In: 6th International Conference on Learning Representations, ICLR 2018-Conference Track Proceedings. vol. 6. International Conference on Representation Learning (2018)
Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28
Uzkent, B., Rangnekar, A., Hoffman, M.J.: Aerial vehicle tracking by adaptive fusion of hyperspectral likelihood maps. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 233–242. IEEE (2017)
Uzkent, B., Rangnekar, A., Hoffman, M.J.: Tracking in aerial hyperspectral videos using deep kernelized correlation filters. IEEE Trans. Geosci. Remote Sens. 57(1), 449–461 (2018)
Wen, Y., Tran, D., Ba, J.: Batchensemble: An alternative approach to efficient ensemble and lifelong learning (2020)
Acknowledgements
This work was supported by the Dynamic Data Driven Applications Systems Program, Air Force Office of Scientific Research under Grant FA9550-19-1-0021. We gratefully acknowledge the support of NVIDIA Corporation with the donations of the Titan X and Titan Xp Pascal GPUs used for this research.
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
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Rangnekar, A., Ientilucci, E., Kanan, C., Hoffman, M.J. (2020). Uncertainty Estimation for Semantic Segmentation of Hyperspectral Imagery. In: Darema, F., Blasch, E., Ravela, S., Aved, A. (eds) Dynamic Data Driven Applications Systems. DDDAS 2020. Lecture Notes in Computer Science(), vol 12312. Springer, Cham. https://doi.org/10.1007/978-3-030-61725-7_20
Download citation
DOI: https://doi.org/10.1007/978-3-030-61725-7_20
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-61724-0
Online ISBN: 978-3-030-61725-7
eBook Packages: Computer ScienceComputer Science (R0)