Abstract
Siamese Neural Networks (SNNs) are deep metric learners that use paired instance comparisons to learn similarity. The neural feature maps learnt in this way provide useful representations for classification tasks. Learning in SNNs is not reliant on explicit class knowledge; instead they require knowledge about the relationship between pairs. Though often ignored, we have found that appropriate pair selection is crucial to maximising training efficiency, particularly in scenarios where examples are limited. In this paper, we study the role of informed pair selection and propose a 2-phased strategy of exploration and exploitation. Random sampling provides the needed coverage for exploration, while areas of uncertainty modeled by neighbourhood properties of the pairs drive exploitation. We adopt curriculum learning to organise the ordering of pairs at training time using similarity knowledge as a heuristic for pair sorting. The results of our experimental evaluation show that these strategies are key to optimising training.
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 code associated with this paper is publicly accessible from https://github.com/RGU-AI/Informed-Pair-Selection.
- 2.
The SelfBACK project is funded by European Union’s H2020 research and innovation programme under grant agreement No. 689043. More details available: http://www.selfback.eu. The SelfBACK dataset associated with this paper is publicly accessible from https://github.com/selfback/activity-recognition.
References
Bengio, Y., Louradour, J., Collobert, R., Weston, J.: Curriculum learning. In: Proceedings of the 26th Annual International Conference on Machine Learning, ICML 2009, pp. 41–48. ACM, New York, June 2009
Bromley, J., Guyon, I., LeCun, Y.: Signature verification using a ‘siamese’ time delay neural network. Int. J. Pattern Recognit. Artif. Intell. 7(4), 669–688 (1993)
Chopra, S., Hadsell, R., LeCun, Y.: Learning a similarity metric discriminatively, with application to face verification. In: Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005, pp. 539–546. IEEE Computer Society, Washington, DC, June 2005
Deng, K., Zheng, Y., Bourke, C., Scott, S., Masciale, J.: New algorithms for budgeted learning. Mach. Learn. 90(1), 59–90 (2013)
Hoffer, E., Ailon, N.: Deep metric learning using triplet network. In: Feragen, A., Pelillo, M., Loog, M. (eds.) SIMBAD 2015. LNCS, vol. 9370, pp. 84–92. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24261-3_7
Koch, G., Zemel, R., Salakhutdinov, R.: Siamese neural networks for one-shot image recognition. In: Deep Learning Workshop, ICML 2015, July 2015
Kumar, M.P., Packer, B., Koller, D.: Self-paced learning for latent variable models. In: Advances in Neural Information Processing Systems, NIPS 2010, vol. 23, pp. 1189–1197. Curran Associates Inc., Red Hook, December 2010
Le, Q., Mikolov, T.: Distributed representations of sentences and documents. In: Proceedings of the 31st International Conference on International Conference on Machine Learning, ICML 2014, vol. 32. pp. II-1188–II-1196. JMLR.org (2014)
Lizotte, D.J., Madani, O., Greiner, R.: Budgeted learning of naive-bayes classifiers. In: Proceedings of the Nineteenth Conf. on Uncertainty in Artificial Intelligence, UAI 2003, pp. 378–385. Morgan Kaufmann Publishers Inc., San Francisco, August 2003
Loshchilov, I., Hutter, F.: Online batch selection for faster training of neural networks. In: ICLR Workshops, ICLR 2016, May 2016
Maas, A.L., Daly, R.E., Pham, P.T., Huang, D., Ng, A.Y., Potts, C.: Learning word vectors for sentiment analysis. In: Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, HLT 2011, vol. 1. pp. 142–150. Association for Computational Linguistics, Stroudsburg (2011)
Massie, S., Craw, S., Wiratunga, N.: Complexity-guided case discovery for case-based reasoning. In: Proceedings of the 20th AAAI Conference on AI, pp. 216–221. AAAI Press (2005)
Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. CoRR abs/1301.3781 (2013)
Pentina, A., Sharmanska, V., Lampert, C.H.: Curriculum learning of multiple tasks. In: Proceedings of the 2015 IEEE Computer Society Conference on Computer Vision and Patter Recognition, CVPR 2015, pp. 5492–5500. IEEE Computer Society, Washington, DC, June 2015
Sani, S., Wiratunga, N., Massie, S., Cooper, K.: SELFBACK—activity recognition for self-management of low back pain. In: Bramer, M., Petridis, M. (eds.) Research and Development in Intelligent Systems XXXIII, pp. 281–294. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-47175-4_21
Sani, S., Wiratunga, N., Massie, S., Cooper, K.: kNN sampling for personalised human activity recognition. In: Aha, D.W., Lieber, J. (eds.) ICCBR 2017. LNCS (LNAI), vol. 10339, pp. 330–344. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-61030-6_23
Schroff, F., Kalenichenko, D., Philbin, J.: Facenet: a unified embedding for face recognition and clustering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015, pp. 815–823. IEEE Computer Society, Washington, DC, June 2015
Shapire, R.E.: The boosting approach to machine learning: An overview. In: Denison, D.D., Hansen, M.H., Holmes, C.C., Mallick, B., Yu, B. (eds.) Nonlinear Estimation and Classification. LNS, vol. 171, pp. 149–172. Springer, New York (2003). https://doi.org/10.1007/978-0-387-21579-2_9
Vinyals, O., Blundell, C., Lillicrap, T., kavukcuoglu, k., Wierstra, D.: Matching networks for one shot learning. In: Lee, D.D., Sugiyama, M., Luxburg, U.V., Guyon, I., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 29, pp. 3630–3638. Curran Associates, Inc. (2016)
Wang, J., et al.: Learning fine-grained image similarity with deep ranking. In: Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014, Washington, DC, USA, pp. 1386–1393. IEEE Computer Society, June 2014. https://doi.org/10.1109/cvpr.2014.180
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Martin, K., Wiratunga, N., Massie, S., Clos, J. (2018). Informed Pair Selection for Self-paced Metric Learning in Siamese Neural Networks. In: Bramer, M., Petridis, M. (eds) Artificial Intelligence XXXV. SGAI 2018. Lecture Notes in Computer Science(), vol 11311. Springer, Cham. https://doi.org/10.1007/978-3-030-04191-5_3
Download citation
DOI: https://doi.org/10.1007/978-3-030-04191-5_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-04190-8
Online ISBN: 978-3-030-04191-5
eBook Packages: Computer ScienceComputer Science (R0)