Abstract
Few-shot learning aims to learn a classifier using a few labelled instances for each class. Metric-learning approaches for few-shot learning embed instances into a high-dimensional space and conduct classification based on distances among instance embeddings. However, such instance embeddings are usually shared across all episodes and thus lack the discriminative power to generalize classifiers according to episode-specific features. In this paper, we propose a novel approach, namely Episode Adaptive Embedding Network (EAEN), to learn episode-specific embeddings of instances. By leveraging the probability distributions of all instances in an episode at each channel-pixel embedding dimension, EAEN can not only alleviate the overfitting issue encountered in few-shot learning tasks, but also capture discriminative features specific to an episode. To empirically verify the effectiveness and robustness of EAEN, we have conducted extensive experiments on three widely used benchmark datasets, under various combinations of different generic embedding backbones and different classifiers. The results show that EAEN significantly improves classification accuracy about 10–20% in different settings over the state-of-the-art methods.
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
Similar content being viewed by others
Notes
- 1.
- 2.
Our code is available at https://www.dropbox.com/s/cll23kem3yswg96/EAEN.zip?dl=0.
References
Allen, K.R., Shelhamer, E., Shin, H., Tenenbaum, J.B.: Infinite mixture prototypes for few-shot learning. ar**v preprint ar**v:1902.04552 (2019)
Antoniou, A., Edwards, H., Storkey, A.: How to train your MAML. In: ICLR (2018)
Bertinetto, L., Henriques, J.F., Torr, P.H., Vedaldi, A.: Meta-learning with differentiable closed-form solvers. ar**v preprint ar**v:1805.08136 (2018)
Chen, W.Y., Liu, Y.C., Kira, Z., Wang, Y.C.F., Huang, J.B.: A closer look at few-shot classification. ar**v preprint ar**v:1904.04232 (2019)
Finn, C., Abbeel, P., Levine, S.: Model-agnostic meta-learning for fast adaptation of deep networks. In: ICML, pp. 1126–1135 (2017)
Garcia, V., Estrach, J.B.: Few-shot learning with graph neural networks. In: ICLR (2018)
Han, C., Shan, S., Kan, M., Wu, S., Chen, X.: Meta-learning with individualized feature space for few-shot classification (2018)
Hariharan, B., Girshick, R.: Low-shot visual recognition by shrinking and hallucinating features. In: ICCV, pp. 3018–3027 (2017)
Kim, J., Kim, T., Kim, S., Yoo, C.D.: Edge-labeling graph neural network for few-shot learning. In: CVPR, pp. 11–20 (2019)
Lee, K., Maji, S., Ravichandran, A., Soatto, S.: Meta-learning with differentiable convex optimization. In: CVPR, pp. 10657–10665 (2019)
Li, H., Eigen, D., Dodge, S., Zeiler, M., Wang, X.: Finding task-relevant features for few-shot learning by category traversal. In: CVPR, pp. 1–10 (2019)
Li, W., Xu, J., Huo, J., Wang, L., Gao, Y., Luo, J.: Distribution consistency based covariance metric networks for few-shot learning. In: AAAI, vol. 33, pp. 8642–8649 (2019)
Liu, Y., et al.: Learning to propagate labels: transductive propagation network for few-shot learning. In: International Conference on Learning Representations (ICLR) (2019)
Nichol, A., Achiam, J., Schulman, J.: On first-order meta-learning algorithms. ar**v preprint ar**v:1803.02999 (2018)
Oreshkin, B., López, P.R., Lacoste, A.: TADAM: task dependent adaptive metric for improved few-shot learning. In: NeurIPS, pp. 721–731 (2018)
Snell, J., Swersky, K., Zemel, R.: Prototypical networks for few-shot learning. In: NeurIPS, pp. 4077–4087 (2017)
Sun, Q., Liu, 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., **ang, T., Torr, P.H., Hospedales, T.M.: Learning to compare: relation network for few-shot learning. In: CVPR, pp. 1199–1208 (2018)
Vinyals, O., Blundell, C., Lillicrap, T., Wierstra, D., et al.: Matching networks for one shot learning. In: NeurIPS, pp. 3630–3638 (2016)
Wang, X., Yu, F., Wang, R., Darrell, T., Gonzalez, J.E.: TAFE-Net: task-aware feature embeddings for low shot learning. In: CVPR, pp. 1831–1840 (2019)
Wang, Y.X., Girshick, R., Hebert, M., Hariharan, B.: Low-shot learning from imaginary data. In: CVPR, pp. 7278–7286 (2018)
Wei, X.S., Wang, P., Liu, L., Shen, C., Wu, J.: Piecewise classifier map**s: learning fine-grained learners for novel categories with few examples. TIP 28(12), 6116–6125 (2019)
Yang, L., Li, L., Zhang, Z., Zhou, X., Zhou, E., Liu, Y.: DPGN: distribution propagation graph network for few-shot learning. In: CVPR, pp. 13390–13399 (2020)
Ye, H.J., Hu, H., Zhan, D.C., Sha, F.: Few-shot learning via embedding adaptation with set-to-set functions. In: CVPR, pp. 8808–8817 (2020)
Zhang, R., Che, T., Ghahramani, Z., Bengio, Y., Song, Y.: MetaGAN: an adversarial approach to few-shot learning. In: NeurIPS, pp. 2365–2374 (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Liu, F., Wang, Q. (2021). Episode Adaptive Embedding Networks for Few-Shot Learning. In: Karlapalem, K., et al. Advances in Knowledge Discovery and Data Mining. PAKDD 2021. Lecture Notes in Computer Science(), vol 12714. Springer, Cham. https://doi.org/10.1007/978-3-030-75768-7_1
Download citation
DOI: https://doi.org/10.1007/978-3-030-75768-7_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-75767-0
Online ISBN: 978-3-030-75768-7
eBook Packages: Computer ScienceComputer Science (R0)