Abstract
Learning from few samples is a major challenge for parameter-rich models such as deep networks. In contrast, people can learn complex new concepts even from very few examples, suggesting that the sample complexity of learning can often be reduced. We describe an approach to reduce the number of samples needed for learning using per-sample side information. Specifically, we show how to speed up learning by providing textual information about feature relevance, like the presence of objects in a scene or attributes in an image. We also give an improved generalization error bound for this case. We formulate the learning problem using an ellipsoid-margin loss, and develop an algorithm that minimizes this loss effectively. Empirical evaluation on two machine vision benchmarks for scene classification and fine-grain bird classification demonstrate the benefits of this approach for few-shot learning.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Atzmon, Y., Chechik, G.: Probabilistic and-or attribute grouping for zero-shot learning. In: UAI (2018)
Atzmon, Y., Chechik, G.: Adaptive confidence smoothing for generalized zero-shot learning. In: CVPR (2019)
Branson, S., et al.: Visual recognition with humans in the loop. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6314, pp. 438–451. Springer, Heidelberg (2010). https://doi.org/10.1007/978-3-642-15561-1_32
Chechik, G., Heitz, G., Elidan, G., Abbeel, P., Koller, D.: Max-margin classification of incomplete data. In: NIPS, pp. 233–240 (2007)
Crammer, K., Dekel, O., Keshet, J., Shalev-Shwartz, S., Singer, Y.: Online passive-aggressive algorithms. J. Mach. Learn. Res. 7(Mar), 551–585 (2006)
Dasgupta, S., Dey, A., Roberts, N., Sabato, S.: Learning from discriminative feature feedback. In: NIPS, pp. 3955–3963 (2018)
Druck, G., Mann, G., McCallum, A.: Reducing annotation effort using generalized expectation criteria. Technical report, Mass. Univ Amherst (2007)
Fang, H., et al.: From captions to visual concepts and back. In: CVPR (2015)
Finn, C., Abbeel, P., Levine, S.: Model-agnostic meta-learning for fast adaptation of deep networks. In: International Conference on Machine Learning, vol. 70, pp 1126–1135 (2017)
Hariharan, B., Girshick, R.: Low-shot visual recognition by shrinking and hallucinating features. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3018–3027 (2017)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770–778 (2016)
Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740–755. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10602-1_48
Poulis, S., Dasgupta, S.: Learning with feature feedback: from theory to practice. In: Artificial Intelligence and Statistics, pp. 1104–1113 (2017)
Raghavan, H., Madani, O., Jones, R.: Active learning with feedback on features and instances. J. Mach. Learn. Res. 7, 1655–1686 (2006)
Ravi, S., Larochelle, H.: Optimization as a model for few-shot learning. In: ICLR (2017)
Shalev-Shwartz, S., Singer, Y.: A new perspective on an old perceptron algorithm. In: Auer, P., Meir, R. (eds.) COLT 2005. LNCS (LNAI), vol. 3559, pp. 264–278. Springer, Heidelberg (2005). https://doi.org/10.1007/11503415_18
Small, K., Wallace, B., Trikalinos, T., Brodley, C.E.: The constrained weight space SVM: learning with ranked features. In: ICML, pp. 865–872 (2011)
Snell, J., Swersky, K., Zemel, R.: Prototypical networks for few-shot learning. In: NIPS, pp. 4077–4087 (2017)
Vinyals, O., Blundell, C., Lillicrap, T., Wierstra, D., et al.: Matching networks for one shot learning. In: NIPS, pp. 3630–3638 (2016)
Visotsky, R., Atzmon, Y., Chechik, G.: Few-shot learning with per-sample rich supervision. arXiv preprint arXiv:1906.03859 (2019)
Welinder, P., et al.: Caltech-UCSD Birds 200. Technical report CNS-TR-2010-001, CalTech (2010)
Xiao, J., Hays, J., Ehinger, K.A., Oliva, A., Torralba, A.: Sun database: large-scale scene recognition from abbey to zoo. In: CVPR, pp. 3485–3492 (2010)
Acknowledgement
Supported by the Israeli Science Foundation grant 737/18.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Visotsky, R., Atzmon, Y., Chechik, G. (2019). Learning with Per-Sample Side Information. In: Hammer, P., Agrawal, P., Goertzel, B., Iklé, M. (eds) Artificial General Intelligence. AGI 2019. Lecture Notes in Computer Science(), vol 11654. Springer, Cham. https://doi.org/10.1007/978-3-030-27005-6_21
Download citation
DOI: https://doi.org/10.1007/978-3-030-27005-6_21
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-27004-9
Online ISBN: 978-3-030-27005-6
eBook Packages: Computer ScienceComputer Science (R0)