Abstract
Few-shot learning requires to recognize novel classes with scarce labeled data. Prototypical network is useful in existing researches, however, training on narrow-size distribution of scarce data usually tends to get biased prototypes. In this paper, we figure out two key influencing factors of the process: the intra-class bias and the cross-class bias. We then propose a simple yet effective approach for prototype rectification in transductive setting. The approach utilizes label propagation to diminish the intra-class bias and feature shifting to diminish the cross-class bias. We also conduct theoretical analysis to derive its rationality as well as the lower bound of the performance. Effectiveness is shown on three few-shot benchmarks. Notably, our approach achieves state-of-the-art performance on both miniImageNet (70.31% on 1-shot and 81.89% on 5-shot) and tieredImageNet (78.74% on 1-shot and 86.92% on 5-shot).
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
References
Allen, K., Shelhamer, E., Shin, H., Tenenbaum, J.: Infinite mixture prototypes for few-shot learning. In: ICML, pp. 232–241 (2019)
Andrychowicz, M., et al.: Learning to learn by gradient descent by gradient descent. In: NIPS, pp. 3981–3989 (2016)
Chen, W.Y., Liu, Y.C., Kira, Z., Wang, Y.C.F., Huang, J.B.: A closer look at few-shot classification. In: ICLR (2019)
Dhillon, G.S., Chaudhari, P., Ravichandran, A., Soatto, S.: A baseline for few-shot image classification. In: ICLR (2020)
Fei-Fei, L., Fergus, R., Perona, P.: One-shot learning of object categories 28, 594–611 (2006)
Finn, C., Abbeel, P., Levine, S.: Model-agnostic meta-learning for fast adaptation of deep networks. In: ICML, pp. 1126–1135 (2017)
Gidaris, S., Bursuc, A., Komodakis, N., Perez, P.P., Cord, M.: Boosting few-shot visual learning with self-supervision. In: ICCV, pp. 8058–8067 (2019)
Gidaris, S., Komodakis, N.: Dynamic few-shot visual learning without forgetting. In: CVPR, pp. 4367–4375 (2018)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770–778 (2016)
Joachims, T.: Transductive inference for text classification using support vector machines. In: ICML, pp. 200–209 (1999)
Kim, J., Kim, T., Kim, S., Yoo, C.D.: Edge-labeling graph neural network for few-shot learning. In: CVPR, pp. 11–20 (2019)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks 141, 1097–1105 (2012)
Lee, K., Maji, S., Ravichandran, A., Soatto, S.: Meta-learning with differentiable convex optimization. In: CVPR, pp. 10657–10665 (2019)
Li, X., et al.: Learning to self-train for semi-supervised few-shot classification. In: NeurIPS (2019)
Li, Z., Zhou, F., Chen, F., Li, H.: Meta-SGD: learning to learn quickly for few shot learning (2017)
Liu, Y., et al.: Learning to propagate labels: transductive propagation network for few-shot learning. In: ICLR (2019)
Miller, E., Matsakis, N., Viola, P.: Learning from one example through shared densities on transforms. In: CVPR, vol. 1, pp. 464–471 (2000)
Mishra, N., Rohaninejad, M., Chen, X., Abbeel, P.: A simple neural attentive meta-learner. In: ICLR (2018)
Munkhdalai, T., Yuan, X., Mehri, S., Trischler, A.: Rapid adaptation with conditionally shifted neurons. In: ICML, pp. 3661–3670 (2018)
Nichol, A., Achiam, J., Schulman, J.: On first-order meta-learning algorithms (2018)
Nowozin, S.: Optimal decisions from probabilistic models: the intersection-over-union case. In: CVPR, pp. 548–555 (2014)
Oreshkin, B.N., Lpez, P.R., Lacoste, A.: TADAM: task dependent adaptive metric for improved few-shot learning. In: NIPS, pp. 721–731 (2018)
Qiao, S., Liu, C., Shen, W., Yuille, A.L.: Few-shot image recognition by predicting parameters from activations. In: CVPR, pp. 7229–7238 (2018)
Ravi, S., Larochelle, H.: Optimization as a model for few-shot learning. In: ICLR (2017)
Ren, M., et al.: Meta-learning for semi-supervised few-shot classification. In: ICLR (2018)
Rice, S.H.: The expected value of the ratio of correlated random variables. Texas Tech University (2015)
Russakovsky, O., et al.: ImageNet large scale visual recognition challenge 115, 211–252 (2015)
Rusu, A.A., et al.: Meta-learning with latent embedding optimization. In: ICLR (2019)
Satorras, V.G., Estrach, J.B.: Few-shot learning with graph neural networks. In: ICLR (2018)
Snell, J., Swersky, K., Zemel, R.S.: Prototypical networks for few-shot learning. In: NIPS, pp. 4077–4087 (2017)
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)
Triantafillou, E., et al.: Meta-dataset: a dataset of datasets for learning to learn from few examples. In: ICLR (2020)
Vinyals, O., Blundell, C., Lillicrap, T.P., Kavukcuoglu, K., Wierstra, D.: Matching networks for one shot learning. In: NIPS, pp. 3637–3645 (2016)
Wang, Y., Li, W., Dai, D., Gool, L.V.: Deep domain adaptation by geodesic distance minimization. In: ICCVW, pp. 2651–2657 (2017)
Zagoruyko, S., Komodakis, N.: Wide residual networks. In: BMVC (2016)
Zhou, D., Bousquet, O., Lal, T.N., Weston, J., Schlkopf, B.: Learning with local and global consistency. In: NIPS, pp. 321–328 (2003)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Liu, J., Song, L., Qin, Y. (2020). Prototype Rectification for Few-Shot Learning. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, JM. (eds) Computer Vision – ECCV 2020. ECCV 2020. Lecture Notes in Computer Science(), vol 12346. Springer, Cham. https://doi.org/10.1007/978-3-030-58452-8_43
Download citation
DOI: https://doi.org/10.1007/978-3-030-58452-8_43
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-58451-1
Online ISBN: 978-3-030-58452-8
eBook Packages: Computer ScienceComputer Science (R0)