Abstract
Metric-based few-shot methods learn to recognize object categories from one or a few examples according to the distances between class features and query samples. The predicting labels of query samples are the same as those of the nearest class features. However, a single metric criterion can not model the distributions of different datasets very well. To get the more suitable metrics for a specified dataset, we propose a Multi-Metric Joint Discrimination Network (MMJDN) in this paper. Firstly, Deep Metric Module (DMM) is introduced to catch the complex relation between each pair of class features and query samples. Secondly, Adaptive Weights Module (AWM) is proposed to generate adaptive weights for different metric criteria. Our method is evaluated on three datasets: miniImageNet, Fewshot-Cifar100 (FC100) and Virus Texture Dataset (Virus15). The experimental results show that MMJDN provides positive performance for few-shot learning compared with some baselines.
The first author is a student.
This research is supported by the National Natural Science Foundation of China (11701357, 11971296, 81830058, 61976132), and The Capacity Construction Project of Local Universities in Shanghai under Grant (18010500600).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Andrychowicz, M., et al.: Learning to learn by gradient descent by gradient descent. In: NeurIPS, pp. 3981–3989 (2016)
Chen, M.T., et al.: Diversity transfer network for few-shot learning. AAAI 34, 10559–10566 (2020)
Finn, C., Abbeel, P., Levine, S.: Model-agnostic meta-learning for fast adaptation of deep networks. ICML 70, 1126–1135 (2017)
Goldberger, J., Hinton, G.E., Roweis, S.T., Salakhutdinov, R.: Neighbourhood components analysis. In: NeurIPS, pp. 513–520 (2004)
Hariharan, B., Girshick, R.: Low-shot visual recognition by shrinking and hallucinating features. In: ICCV, pp. 3037–3046 (2017)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Koch, G.: Siamese neural networks for one-shot image recognition. Ph.D. thesis, University of Toronto (2015)
Krizhevsky, A.: Learning multiple layers of features from tiny images. Master’s thesis, University of Tront (2009)
Lake, B.M., Salakhutdinov, R., Gross, J., Tenenbaum, J.B.: One shot learning of simple visual concepts. CogScI 33(33), 2568–2573 (2011)
Lake, B.M., Salakhutdinov, R., Tenenbaum, J.B.: Human-level concept learning through probabilistic program induction. Sci. 350(6266), 1332–1338 (2015)
Lake, B.M., Ullman, T.D., Tenenbaum, J.B., Gershman, S.J.: Building machines that learn and think like people. BBS 40, e253 (2017)
Liu, Y., Lee, J., Park, M., Kim, S., Yang, Y.: Learning to propagate labels: transductive propagation network for few-shot learning. In: ICLR, pp. 1–14 (2019)
Miller, E.G., Matsakis, N.E., Viola, P.A.: Learning from one example through shared densities on transforms. In: CVPR, pp. 464–471 (2000)
Min, R., Stanley, D.A., Yuan, Z., Bonner, A., Zhang, Z.: A deep non-linear feature mapping for large-margin knn classification. In: ICDM, pp. 357–366 (2009)
Munkhdalai, T., Yu, H.: Meta networks. ICML 70, 2554–2563 (2017)
Oreshkin, B.N., Rodriguez, P., Lacoste, A.: Tadam: task dependent adaptive metric for improved few-shot learning. In: NeurIPS, pp. 721–731 (2018)
Ravi, S., Larochelle, H.: Optimization as a model for few-shot learning. In: ICLR, pp. 1–11 (2016)
Santoro, A., Bartunov, S., Botvinick, M., Wierstra, D., Lillicrap, T.: Meta-learning with memory-augmented neural networks. ICML 48, 1842–1850 (2016)
Schmidhuber, J., Zhao, J., Wiering, M.: Shifting inductive bias with success-story algorithm, adaptive levin search, and incremental self-improvement. Mach. Learn. 28(1), 105–130 (1997)
Schmidt, L.A.: Meaning and compositionality as statistical induction of categories and constraints. Ph.D. thesis, MIT (2018)
Snell, J., Swersky, K., Zemel, R.S.: Prototypical networks for few-shot learning. In: NeurIPS, pp. 4080–4090 (2017)
Sun, Q.R., Liu, Y.Y., Chua, T.S., Schiele, B.: Meta-transfer learning for few-shot learning. In: CVPR, pp. 403–412 (2019)
Sung, F., Yang, Y., Zhang, L., Xiang, T., Torr, P.H., Hospedales, T.M.: Learning to compare: relation network for few-shot learning. In: CVPR, pp. 1199–1208 (2018)
Thrun, S., Pratt, L.: Learning to learn: Introduction and overview. In: Thrun, S., Pratt, L. (eds.) Learning to Learn, pp. 3–17. Springer, Boston, MA (1998). https://doi.org/10.1007/978-1-4615-5529-2_1
Vinyals, O., Blundell, C., Lillicrap, T., Kavukcuoglu, K., Wierstra, D.: Matching networks for one shot learning. In: NeurIPS, pp. 3630–3638 (2016)
Wang, Y.X., Girshick, R., Hebert, M., Hariharan, B.: Low-shot learning from imaginary data. In: CVPR, pp. 7278–7286 (2018)
Weinberger, K.Q., Blitzer, J., Saul, L.K.: Distance metric learning for large margin nearest neighbor classification. In: NeurIPS, pp. 1473–1480 (2005)
Xu, J.W., Wang, X.G., Feng, B., Liu, W.Y.: Deep multi-metric learning for text-independent speaker verification. Neurocomput. 410(410), 394–400 (2020)
Yoon, J., Kim, T., Dia, O., Kim, S., Bengio, Y., Ahn, S.: Bayesian model-agnostic meta-learning. In: NeurIPS, pp. 7332–7342 (2018)
Zhou, P., Yuan, X.T., Xu, H., Yan, S.C., Feng, J.S.: Efficient meta learning via minibatch proximal update. In: NeurIPS, pp. 1534–1544 (2019)
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Wang, W., Wen, Z., Ma, L., Ying, S. (2020). Multi-metric Joint Discrimination Network for Few-Shot Classification. In: Peng, Y., et al. Pattern Recognition and Computer Vision. PRCV 2020. Lecture Notes in Computer Science(), vol 12307. Springer, Cham. https://doi.org/10.1007/978-3-030-60636-7_23
Download citation
DOI: https://doi.org/10.1007/978-3-030-60636-7_23
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-60635-0
Online ISBN: 978-3-030-60636-7
eBook Packages: Computer ScienceComputer Science (R0)