Abstract
Deep learning has proven itself as a successful set of models for learning useful semantic representations of data. These, however, are mostly implicitly learned as part of a classification task. In this paper we propose the triplet network model, which aims to learn useful representations by distance comparisons. A similar model was defined by Wang et al. (2014), tailor made for learning a ranking for image information retrieval. Here we demonstrate using various datasets that our model learns a better representation than that of its immediate competitor, the Siamese network. We also discuss future possible usage as a framework for unsupervised learning.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Bengio, Y.: Learning Deep Architectures for AI (2009). ISSN 1935–8237
Bengio, Y.: Deep learning of representations: looking forward. In: Dediu, A.-H., Martín-Vide, C., Mitkov, R., Truthe, B. (eds.) SLSP 2013. LNCS, vol. 7978, pp. 1–37. Springer, Heidelberg (2013)
Bromley, J., Bentz, J.W., Bottou, L., Guyon, I., LeCun, Y., Moore, C., Säckinger, E., Shah, R.: Signature verification using a time delay neural network. Int. J. Pattern Recogn. Artif. Intell. 7(04), 669–688 (1993)
Chechik, G., Sharma, V., Shalit, U., Bengio, S.: Large scale online learning of image similarity through ranking. J. Mach. Learn. Res. 11, 1109–1135 (2010)
Chopra, S., Hadsell, R., LeCun, Y.: Learning a similarity metric discriminatively, with application to face verification. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 539–546 (2005). ISBN 0769523722
Coates, A., Ng, A.Y., Lee, H.: An analysis of single-layer networks in unsupervised feature learning. In: International Conference on Artificial Intelligence and Statistics, pp. 215–223 (2011)
Collobert, R., Kavukcuoglu, K., Farabet, C.: Torch7: A matlab-like environment for machine learning. In: BigLearn, NIPS Workshop, number EPFL-CONF-192376 (2011)
Goodfellow, I.J., Warde-Farley, D., Mirza, M., Courville, A., Bengio, Y.: Maxout networks (2013). arXiv preprint arXiv:1302.4389
Hadsell, R., Chopra, S., LeCun, Y.: Dimensionality reduction by learning an invariant mapping. In: 2006 IEEE computer society conference on Computer vision and pattern recognition, vol. 2, pp. 1735–1742. IEEE (2006)
Hinton, G.E.: Learning multiple layers of representation (2007). ISSN 13646613
Krizhevsky, A. Hinton, G.: Learning multiple layers of features from tiny images. Computer Science Department, University of Toronto, Technical report (2009)
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)
Lee, C.-Y., Xie, S., Gallagher, P., Zhang, Z., Tu, Z.: Deeply-supervised nets (2014). arXiv preprint arXiv:1409.5185
Lin, M., Chen, Q., Yan, S.: Network in network. CoRR, abs/1312.4400 (2013). http://arxiv.org/abs/1312.4400
Lin, T.-H. Kung, H.T.: Stable and efficient representation learning with nonnegativity constraints. In Proceedings of the 31st International Conference on Machine Learning (ICML 2014), pp. 1323–1331 (2014)
Mairal, J., Koniusz, P., Harchaoui, Z., Schmid, C.: Convolutional kernel networks. In: Advances in Neural Information Processing Systems, pp. 2627–2635 (2014)
Mobahi, H., Collobert, R., Weston, J.: Deep learning from temporal coherence in video. In: Proceedings of the 26th Annual International Conference on Machine Learning, pp. 737–744. ACM (2009)
Netzer, Y., Wang, T., Coates, A., Bissacco, A., Wu, B., Ng, A.Y.: Reading digits in natural images with unsupervised feature learning (2011)
Razavian, A.S., Azizpour, H., Sullivan, J., Carlsson, S.: CNN Features off-the-shelf: an Astounding Baseline for Recognition (2014). Arxiv http://arxiv.org/abs/1403.6382
Sermanet, P., Eigen, D., Zhang, X., Mathieu, M., Fergus, R., LeCun, Y.: OverFeat : Integrated Recognition, Localization and Detection using Convolutional Networks, pp. 1–15 (2013). arXiv preprint arXiv:1312.6229, http://arxiv.org/abs/1312.6229
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich, A.: Going deeper with convolutions. CoRR, abs/1409.4842 (2014). http://arxiv.org/abs/1409.4842
Tamuz, O., Liu, C., Belongie, S., Shamir, O., Kalai, A.: Adaptively learning the crowd kernel. In: Getoor, L., Scheffer, T. (eds.) Proceedings of the 28th International Conference on Machine Learning (ICML-11), ICML 2011, pp. 673–680. ACM, New York (2011). ISBN 978-1-4503-0619-5
Wang, J., Song, Y., Leung, T., Rosenberg, C., Wang, J., Philbin, J., Chen, B., Wu. Y.: Learning fine-grained image similarity with deep ranking In: CVPR (2014)
Zeiler, M.D., Fergus, R.: Visualizing and Understanding Convolutional Networks (2013). arXiv preprint arXiv:1311.2901, http://arxiv.org/abs/1311.2901
Zeiler, M.D., Fergus, R.: Stochastic pooling for regularization of deep convolutional neural networks (2013). arXiv preprint arXiv:1301.3557
Acknowledgements
We gratefully acknowledge the support of NVIDIA Corporation with the donation of the Titan-Z GPU used for this research. This research was additionally supported by the Israel Science Foundation (ISF) grant No. 1271/13, and by the ISF-UGC India-Israel joint research program grant No. 1932/14.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Hoffer, E., Ailon, N. (2015). Deep Metric Learning Using Triplet Network. In: Feragen, A., Pelillo, M., Loog, M. (eds) Similarity-Based Pattern Recognition. SIMBAD 2015. Lecture Notes in Computer Science(), vol 9370. Springer, Cham. https://doi.org/10.1007/978-3-319-24261-3_7
Download citation
DOI: https://doi.org/10.1007/978-3-319-24261-3_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-24260-6
Online ISBN: 978-3-319-24261-3
eBook Packages: Computer ScienceComputer Science (R0)