Abstract
Few-shot learning methods aim to embed the data to a low-dimensional embedding space and then classify the unseen query data to the seen support set. While these works assume that the support set and the query set lie in the same embedding space, a distribution shift usually occurs between the support set and the query set, i.e., the Support-Query Shift, in the real world. Though optimal transportation has shown convincing results in aligning different distributions, we find that the small perturbations in the images would significantly misguide the optimal transportation and thus degrade the model performance. To relieve the misalignment, we first propose a novel adversarial data augmentation method, namely Perturbation-Guided Adversarial Alignment (PGADA), which generates the hard examples in a self-supervised manner. In addition, we introduce Regularized Optimal Transportation to derive a smooth optimal transportation plan. Extensive experiments on three benchmark datasets manifest that our framework significantly outperforms the eleven state-of-the-art methods on three datasets. Our code is available at https://github.com/772922440/PGADA.
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.
We employ a 3-layer convolutional neural network as our G.
- 2.
Note that it is valid to access the images from testing set in few-shot learning, which is named transductive few-shot learning [22].
References
Antoniou, A., Storkey, A., Edwards, H.: Data augmentation generative adversarial networks. In: ICLR (2017)
Bennequin, E., Bouvier, V., Tami, M., Toubhans, A., Hudelot, C.: Bridging few-shot learning and adaptation: new challenges of support-query shift. ECML-PKDD (2021)
Bottou, L.: Stochastic gradient descent tricks. In: Montavon, G., Orr, G.B., Müller, KR. (eds) Neural Networks: Tricks of the Trade. LNCS, vol. 7700. Springer, Berlin (2012). https://doi.org/10.1007/978-3-642-35289-8_25
Boudiaf, M., Masud, Z.I., Rony, J., Dolz, J., Piantanida, P., Ayed, I.B.: Transductive information maximization for few-shot learning. arXiv preprint arXiv:2008.11297 (2020)
Caldas, S., et al.: LEAF: a benchmark for federated settings. NeurIPS (2019)
Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: ICML, pp. 1597–1607. PMLR (2020)
Chen, W.Y., Liu, Y.C., Kira, Z., Wang, Y.C.F., Huang, J.B.: A closer look at few-shot classification. arXiv preprint arXiv:1904.04232 (2019)
Courty, N., Flamary, R., Tuia, D., Rakotomamonjy, A.: Optimal transport for domain adaptation. IEEE TPAMI (2016)
Cuturi, M.: Sinkhorn distances: lightspeed computation of optimal transport. NeurIPS 26, 2292–2300 (2013)
Dhillon, G.S., Chaudhari, P., Ravichandran, A., Soatto, S.: A baseline for few-shot image classification. In: ICLR (2019)
Finn, C., Abbeel, P., Levine, S.: Model-agnostic meta-learning for fast adaptation of deep networks. In: ICML (2017)
Garcia, V., Bruna, J.: Few-shot learning with graph neural networks. In: ICLR (2017)
Gong, C., Ren, T., Ye, M., Liu, Q.: MaxUp: Lightweight adversarial training with data augmentation improves neural network training. In: CVPR, pp. 2474–2483 (2021)
Goodfellow, I., et al.: Generative adversarial nets. NeurIPS 27, 2672–2680 (2014)
Hariharan, B., Girshick, R.: Low-shot visual recognition by shrinking and hallucinating features. In: CVPR, pp. 3018–3027 (2017)
Huang, S.W., Lin, C.T., Chen, S.P., Wu, Y.Y., Hsu, P.H., Lai, S.H.: AugGAN: cross domain adaptation with GAN-based data augmentation. In: ECCV, pp. 718–731 (2018)
Jiang, S., Chen, H.W., Chen, M.S.: Dataflow systolic array implementations of exploring dual-triangular structure in QR decomposition using high-level synthesis. In: ICFPT (2021)
Jiang, S., Yao, X., Long, Q., Chen, J., Jiang, H.: Fund investment decision in support vector classification based on information entropy. Rev. Econ. Finance 15, 57–66 (2019)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2014)
Krizhevsky, A., Hinton, G., et al.: Learning multiple layers of features from tiny images (2009)
Liu, Y., et al.: Learning to propagate labels: Transductive propagation network for few-shot learning. In: ICLR (2018)
Phoo, C.P., Hariharan, B.: Self-training for few-shot transfer across extreme task differences. In: ICLR (2020)
Samangouei, P., Kabkab, M., Chellappa, R.: Defense-GAN: protecting classifiers against adversarial attacks using generative models. In: ICLR (2018)
Schonfeld, E., Ebrahimi, S., Sinha, S., Darrell, T., Akata, Z.: Generalized zero-and few-shot learning via aligned variational autoencoders. In: CVPR. pp. 8247–8255 (2019)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: ICLR (2015)
Snell, J., Swersky, K., Zemel, R.S.: Prototypical networks for few-shot learning. In: NeurIPS (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)
Theagarajan, R., Chen, M., Bhanu, B., Zhang, J.: ShieldNets: Defending against adversarial attacks using probabilistic adversarial robustness. In: CVPR, pp. 6988–6996 (2019)
Triantafillou, E., et al.: Meta-dataset: a dataset of datasets for learning to learn from few examples. arXiv preprint arXiv:1903.03096 (2019)
Vinyals, O., Blundell, C., Lillicrap, T., Wierstra, D., et al.: Matching networks for one shot learning. In: NeurIPS (2016)
Wang, Y.X., Girshick, R., Hebert, M., Hariharan, B.: Low-shot learning from imaginary data. In: CVPR, pp. 7278–7286 (2018)
Xie, Q., Luong, M.T., Hovy, E., Le, Q.V.: Self-training with noisy student improves ImageNet classification. In: CVPR, pp. 10687–10698 (2020)
Yun, S., Han, D., Oh, S.J., Chun, S., Choe, J., Yoo, Y.: CutMix: regularization strategy to train strong classifiers with localizable features. In: ICCV, pp. 6023–6032 (2019)
Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: mixup: beyond empirical risk minimization. In: ICLR (2017)
Zhao, A., et al.: Domain-adaptive few-shot learning. In: WACV, pp. 1390–1399 (2021)
Zhao, L., Liu, T., Peng, X., Metaxas, D.: Maximum-entropy adversarial data augmentation for improved generalization and robustness. arXiv preprint arXiv:2010.08001 (2020)
Acknowledgement
S. Jiang is supported by the science and technology plan project in Huizhou (No. 2020SD0402030).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Jiang, S., Ding, W., Chen, HW., Chen, MS. (2022). PGADA: Perturbation-Guided Adversarial Alignment for Few-Shot Learning Under the Support-Query Shift. In: Gama, J., Li, T., Yu, Y., Chen, E., Zheng, Y., Teng, F. (eds) Advances in Knowledge Discovery and Data Mining. PAKDD 2022. Lecture Notes in Computer Science(), vol 13280. Springer, Cham. https://doi.org/10.1007/978-3-031-05933-9_1
Download citation
DOI: https://doi.org/10.1007/978-3-031-05933-9_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-05932-2
Online ISBN: 978-3-031-05933-9
eBook Packages: Computer ScienceComputer Science (R0)