Abstract
Existing methods for geolocating images use standard classification or image retrieval techniques. These methods have poor theoretical properties because they do not take advantage of the earth’s spherical geometry. In some cases, they require training data sets that grow exponentially with the number of feature dimensions. This paper introduces the Mixture of von-Mises Fisher (MvMF) loss function, which is the first loss function that exploits the earth’s spherical geometry to improve geolocation accuracy. We prove that this loss requires only a dataset of size linear in the number of feature dimensions, and empirical results show that our method outperforms previous methods with orders of magnitude less training data and computation.
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
Notes
- 1.
The original PlaNet paper chose a value of \(c\approx 2^{15}\).
- 2.
The dataset originally contained about 14 million images, but many of them have since been deleted from Flickr and so were unavailable to us.
References
Arandjelovic, R., Gronat, P., Torii, A., Pajdla, T., Sivic, J.: NetVLAD: CNN architecture for weakly supervised place recognition. In: CVPR, June 2016
Bachrach, Y., et al.: Speeding up the Xbox recommender system using a Euclidean transformation for inner-product spaces. In: Proceedings of the 8th ACM Conference on Recommender Systems, pp. 257–264. ACM (2014)
Carreira-Perpinan, M.A.: Mode-finding for mixtures of gaussian distributions. TPAMI 22(11), 1318–1323 (2000)
Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: AIStats, pp. 249–256 (2010)
Gopal, S., Yang, Y.: Von Mises-Fisher clustering models. In: ICML, pp. 154–162 (2014)
Hasnat, M., Bohné, J., Milgram, J., Gentric, S., Chen, L., et al.: von Mises-Fisher mixture model-based deep learning: application to face verification. arXiv preprint arXiv:1706.04264 (2017)
Hays, J., Efros, A.A.: IM2GPS: estimating geographic information from a single image. In: CVPR. IEEE (2008)
Hays, J., Efros, A.A.: Large-scale image geolocalization. In: Choi, J., Friedland, G. (eds.) Multimodal Location Estimation of Videos and Images, pp. 41–62. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-09861-6_3
Hazan, E., Koren, T., Levy, K.Y.: Logistic regression: tight bounds for stochastic and online optimization. In: COLT (2014)
He, K., Zhang, X., Ren, S., Sun, J.: Identity mappings in deep residual networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 630–645. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46493-0_38
Kingma, D.P., Adam, J.B.: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Kornblith, S., Shlens, J., Le, Q.V.: Do better ImageNet models transfer better? arXiv preprint arXiv:1805.08974 (2018)
Mardia, K.V., Jupp, P.E.: Directional Statistics. Wiley, Hoboken (2009)
Mousselly-Sergieh, H., Watzinger, D., Huber, B., Döller, M., Egyed-Zsigmond, E., Kosch, H.: World-wide scale geotagged image dataset for automatic image annotation and reverse geotagging. In: MMSys, 2014
Muller-Budack, E., Pustu-Iren, K., Ewerth, R.: Geolocation estimation of photos using a hierarchical model and scene classification. In: ECCV (2018)
Seo, P.H., Weyand, T., Sim, J., Han, B.: CPlaNet: enhancing image geolocalization by combinatorial partitioning of maps. arXiv preprint arXiv:1808.02130 (2018)
Shalev-Shwartz, S., Ben-David, S.: Understanding Machine Learning: From Theory to Algorithms. Cambridge University Press, Cambridge (2014)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
Szegedy, C., et al.: Going deeper with convolutions. In: CVPR (2015)
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: CVPR (2016)
Vo, N., Jacobs, N., Hays, J.: Revisiting IM2GPS in the deep learning era. In: ICCV, pp. 2640–2649. IEEE (2017)
Weyand, T., Kostrikov, I., Philbin, J.: PlaNet - Photo Geolocation with Convolutional Neural Networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 37–55. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46484-8_3
Zagoruyko, S., Komodakis, N.: Wide residual networks. arXiv preprint arXiv:1605.07146 (2016)
Acknowledgments
We thank an anonymous reviewer for identifying a mistake in the first version of our proof. E. Papalexakis was supported by the Department of the Navy, Naval Engineering Education Consortium under award no. N00174-17-1-0005 and the National Science Foundation CDS&E Grant no. OAC-1808591. V. Tsotras was supported by National Science Foundation grants IIS-1527984 and SES-1831615.
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
Izbicki, M., Papalexakis, E.E., Tsotras, V.J. (2020). Exploiting the Earth’s Spherical Geometry to Geolocate Images. In: Brefeld, U., Fromont, E., Hotho, A., Knobbe, A., Maathuis, M., Robardet, C. (eds) Machine Learning and Knowledge Discovery in Databases. ECML PKDD 2019. Lecture Notes in Computer Science(), vol 11907. Springer, Cham. https://doi.org/10.1007/978-3-030-46147-8_1
Download citation
DOI: https://doi.org/10.1007/978-3-030-46147-8_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-46146-1
Online ISBN: 978-3-030-46147-8
eBook Packages: Computer ScienceComputer Science (R0)
