Abstract
Meta-learning aims to learn models that can make quick adaptations to new tasks. However, due to the lack of data, the further improvement of meta-learning can be severely constrained. Since, data augmentation has been a commonly used method to help models reach state-of-art performance in various image classification tasks. It is wise to use data augmentation methods in meta-learning. Different strategies for applying data augmentation to meta-learning have emerged. One common combination of data augmentation and meta-learning is performing different transformations on images. Other methods use generative models, such as GAN, VAE, or AE, to generate samples and expand the data set. In this paper, we proposed a novel data augmentation method aiming to enlarge the number of samples in the support sets. Our approach uses wavelet transform, a widely used method in signal analysis and processing and style mix from AdaIn. Furthermore, we use both ResNet and ViT as our feature encoder. Combining with the idea of contrastive learning, we train our ViT in an unsupervised way. Experimental results show that we achieve a decent performance improvement.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Vilalta, R., Drissi, Y.: A perspective view and survey of meta-learning. Artif. Intell. Rev. 18(2), 77–95 (2002)
Vanschoren, J.: Meta-learning: A survey. arXiv preprint arXiv:1810.03548 (2018)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Adv. Neural. Inf. Process. Syst. 25, 1097–1105 (2012)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Szegedy, C., et al.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–9 (2015)
Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248–255. IEEE (2009)
Ni, R., Goldblum, M., Sharaf, A., Kong, K., Goldstein, T.: Data augmentation for meta-learning. In: International Conference on Machine Learning, pp. 8152–8161. PMLR (2021)
Yun, S., Han, D., Oh, S.J., Chun, S., Choe, J., Yoo, Y.: Cutmix: regularization strategy to train strong classifiers with localizable features. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 6023–6032 (2019)
Zhang, H., Cissé, M., Dauphin, Y.N., Lopez-Paz, D.: mixup: beyond empirical risk minimization. In: 6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, April 30 - May 3, 2018, Conference Track Proceedings. OpenReview.net (2018)
Verma, V., et al.: Manifold mixup: Better representations by interpolating hidden states. In: Chaudhuri, K., Salakhutdinov, R. (eds.) Proceedings of the 36th International Conference on Machine Learning, ICML 2019. Proceedings of Machine Learning Research, vol. 97, pp. 6438–6447. PMLR (2019)
Zhang, R., Che, T., Ghahramani, Z., Bengio, Y., Song, Y.: Metagan: an adversarial approach to few-shot learning. In: NeurIPS, vol. 2, p. 8 (2018)
Lee, D.B., Min, D., Lee, S., Hwang, S.J.: Meta-GMVAE: mixture of gaussian VAE for unsupervised meta-learning. In: International Conference on Learning Representations (2020)
Huang, X., Belongie, S.J.: Arbitrary style transfer in real-time with adaptive instance normalization. In: 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24–26, 2017, Workshop Track Proceedings (2017)
Fu, Y., Xie, Y., Fu, Y., Chen, J., Jiang, Y.G.: Wave-san: Wavelet based style augmentation network for cross-domain few-shot learning. arXiv preprint arXiv:2203.07656 (2022)
Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: 9th International Conference on Learning Representations, ICLR 2021 (2021)
van den Oord, A., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. CoRR abs/1807.03748 (2018)
He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.B.: Momentum contrast for unsupervised visual representation learning. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020, Seattle, WA, USA, June 13–19, 2020, pp. 9726–9735 (2020)
Finn, C., Abbeel, P., Levine, S.: Model-agnostic meta-learning for fast adaptation of deep networks. In: International Conference on Machine Learning, pp. 1126–1135. PMLR (2017)
Rusu, A.A., et al.: Meta-learning with latent embedding optimization. arXiv preprint arXiv:1807.05960 (2018)
Ravi, S., Larochelle, H.: Optimization as a model for few-shot learning (2016)
Li, Z., Zhou, F., Chen, F., Li, H.: Meta-SGD: learning to learn quickly for few-shot learning. arXiv preprint arXiv:1707.09835 (2017)
Vinyals, O., Blundell, C., Lillicrap, T., Wierstra, D., et al.: Matching networks for one shot learning. Adv. Neural. Inf. Process. Syst. 29, 3630–3638 (2016)
Sung, F., Yang, Y., Zhang, L., Xiang, T., Torr, P.H., Hospedales, T.M.: Learning to compare: Relation network for few-shot learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1199–1208 (2018)
Snell, J., Swersky, K., Zemel, R.: Prototypical networks for few-shot learning. In: Guyon, I., et al. (eds.) Advances in Neural Information Processing Systems. vol. 30. Curran Associates, Inc. (2017)
Ni, R., Goldblum, M., Sharaf, A., Kong, K., Goldstein, T.: Data augmentation for meta-learning. CoRR abs/2010.07092 (2020)
Schwartz, E., et al.: Delta-encoder: an effective sample synthesis method for few-shot object recognition. In: Advances in Neural Information Processing Systems, vol. 31 (2018)
Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The caltech-ucsd birds-200-2011 dataset. Technical report CNS-TR-2011-001, California Institute of Technology (2011)
Wang, H., Deng, Z.H.: Cross-domain few-shot classification via adversarial task augmentation. arXiv preprint arXiv:2104.14385 (2021)
Krause, J., Stark, M., Deng, J., Fei-Fei, L.: 3D object representations for fine-grained categorization. In: 4th International IEEE Workshop on 3D Representation and Recognition (3dRR-13). Sydney, Australia (2013)
Sun, Q., Liu, Y., Chua, T.S., Schiele, B.: Meta-transfer learning for few-shot learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 403–412 (2019)
Mishra, N., Rohaninejad, M., Chen, X., Abbeel, P.: A simple neural attentive meta-learner. arXiv preprint arXiv:1707.03141 (2017)
Lee, K., Maji, S., Ravichandran, A., Soatto, S.: Meta-learning with differentiable convex optimization. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10657–10665 (2019)
Chen, Y., Wang, X., Liu, Z., Xu, H., Darrell, T.: A new meta-baseline for few-shot learning. arXiv preprint arXiv:2003.04390 (2020)
Tseng, H.Y., Lee, H.Y., Huang, J.B., Yang, M.H.: Cross-domain few-shot classification via learned feature-wise transformation. In: International Conference on Learning Representations (2020)
Sun, J., Lapuschkin, S., Samek, W., Zhao, Y., Cheung, N.M., Binder, A.: Explanation-guided training for cross-domain few-shot classification. In: 2020 25th International Conference on Pattern Recognition (ICPR), pp. 7609–7616 (2021)
Wang, H., Deng, Z.H.: Cross-domain few-shot classification via adversarial task augmentation. In: Zhou, Z.H. (ed.) Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21, pp. 1075–1081, August 2021. main Track
Acknowledgment
This work is supported by the National Key R &D Program of China (2018YFA0701700; 2018YFA0701701), and the National Natural Science Foundation of China under Grant No. 61672364, No. 62176172 and No. 61902269.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Yu, H., Li, F. (2023). Patch Mix Augmentation with Dual Encoders for Meta-Learning. In: Tanveer, M., Agarwal, S., Ozawa, S., Ekbal, A., Jatowt, A. (eds) Neural Information Processing. ICONIP 2022. Lecture Notes in Computer Science, vol 13623. Springer, Cham. https://doi.org/10.1007/978-3-031-30105-6_2
Download citation
DOI: https://doi.org/10.1007/978-3-031-30105-6_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-30104-9
Online ISBN: 978-3-031-30105-6
eBook Packages: Computer ScienceComputer Science (R0)