Abstract
In this paper, we carefully revisit the issues of conventional few-shot learning: i) gaps in highlighted features between objects in support and query samples, and ii) losing the explicit local properties due to global pooled features. Motivated by them, we propose a novel method to enhance robustness in few-shot learning by aligning prototypes with abundantly informed ones. As a way of providing more information, we smoothly augment the support image by carefully manipulating the discriminative part corresponding to the highest attention score to consistently represent the object without distorting the original information. In addition, we leverage word embeddings of each class label to provide abundant feature information, serving as the basis for closing gaps between prototypes of different branches. The two parallel branches of explicit attention modules independently refine support prototypes and information-rich prototypes. Then, the support prototypes are aligned with superior prototypes to mimic rich knowledge of attention-based smooth augmentation and word embeddings. We transfer the imitated knowledge to queries in a task-adaptive manner and cross-adapt the queries and prototypes to generate crucial features for metric-based few-shot learning. Extensive experiments demonstrate that our method consistently outperforms existing methods on four benchmark datasets.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bertinetto, L., Henriques, J.F., Torr, P., Vedaldi, A.: Meta-learning with differentiable closed-form solvers. In: ICLR (2018)
Bülthoff, H.H., Lee, S.W., Poggio, T., Wallraven, C., et al.: Biologically Motivated Computer Vision: Second International Workshop, BMCV 2002, Tübingen, Germany, November 22–24, 2002, Proceedings, vol. 2525. Springer Science & Business Media (2002)
Chen, C., Yang, X., Xu, C., Huang, X., Ma, Z.: ECKPN: explicit class knowledge propagation network for transductive few-shot learning. In: CVPR, pp. 6596–6605 (2021)
Chen, W.Y., Liu, Y.C., Kira, Z., Wang, Y.C.F., Huang, J.B.: A closer look at few-shot classification. In: ICLR (2018)
Chikontwe, P., Kim, S., Park, S.H.: Cad: co-adapting discriminative features for improved few-shot classification. In: CVPR, pp. 14554–14563 (2022)
Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: CVPR, pp. 248–255 (2009)
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., Pérez, P., Cord, M.: Boosting few-shot visual learning with self-supervision. In: ICCV, pp. 8059–8068 (2019)
Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572 (2014)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770–778 (2016)
He, Y., et al.: Attribute surrogates learning and spectral tokens pooling in transformers for few-shot learning. In: CVPR, pp. 9119–9129 (2022)
Hilliard, N., Phillips, L., Howland, S., Yankov, A., Corley, C.D., Hodas, N.O.: Few-shot learning with metric-agnostic conditional embeddings. arXiv preprint arXiv:1802.04376 (2018)
Hou, R., Chang, H., Ma, B., Shan, S., Chen, X.: Cross attention network for few-shot classification. In: NeurIPS (2019)
Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: CVPR, pp. 7132–7141 (2018)
Huang, H., Zhang, J., Zhang, J., Wu, Q., Xu, C.: PTN: a poisson transfer network for semi-supervised few-shot learning. In: AAAI, pp. 1602–1609 (2021)
Kang, D., Kwon, H., Min, J., Cho, M.: Relational embedding for few-shot classification. In: ICCV, pp. 8822–8833 (2021)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: NeurIPS (2012)
Lee, M.S., Yang, Y.M., Lee, S.W.: Automatic video parsing using shot boundary detection and camera operation analysis. Pattern Recogn. 34(3), 711–719 (2001)
Li, J., Wang, Z., Hu, X.: Learning intact features by erasing-inpainting for few-shot classification. In: AAAI, pp. 8401–8409 (2021)
Liu, Y., Zheng, T., Song, J., Cai, D., He, X.: DMN4: few-shot learning via discriminative mutual nearest neighbor neural network. In: AAAI, pp. 1828–1836 (2022)
Mangla, P., Kumari, N., Sinha, A., Singh, M., Krishnamurthy, B., Balasubramanian, V.N.: Charting the right manifold: manifold mixup for few-shot learning. In: WACV, pp. 2218–2227 (2020)
Nam, W.J., Lee, S.W.: Gradient hedging for intensively exploring salient interpretation beyond neuron activation. arXiv preprint arXiv:2205.11109 (2022)
Pennington, J., Socher, R., Manning, C.D.: Glove: global vectors for word representation. In: EMNLP, pp. 1532–1543 (2014)
Ravi, S., Larochelle, H.: Optimization as a model for few-shot learning. In: ICLR (2016)
Ren, M., et al.: Meta-learning for semi-supervised few-shot classification. In: ICLR (2018)
Roh, M.C., Kim, T.Y., Park, J., Lee, S.W.: Accurate object contour tracking based on boundary edge selection. Pattern Recogn. 40(3), 931–943 (2007)
Rusu, A.A., et al.: Meta-learning with latent embedding optimization. In: ICLR (2018)
Snell, J., Swersky, K., Zemel, R.: 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)
Vaswani, A., et al.: Attention is all you need. In: NeurIPS (2017)
Vinyals, O., et al.: Matching networks for one shot learning. In: NeurIPS, pp. 3630–3638 (2016)
Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The caltech-ucsd birds-200-2011 dataset (2011)
Wertheimer, D., Tang, L., Hariharan, B.: Few-shot classification with feature map reconstruction networks. In: CVPR, pp. 8012–8021 (2021)
Xi, D., Podolak, I.T., Lee, S.W.: Facial component extraction and face recognition with support vector machines. In: Proceedings of Fifth IEEE International Conference on Automatic Face Gesture Recognition, pp. 83–88. IEEE (2002)
Xing, C., Rostamzadeh, N., Oreshkin, B., Pinheiro, O.P.O.: Adaptive cross-modal few-shot learning. In: NeurIPS (2019)
Yang, F., Wang, R., Chen, X.: Sega: semantic guided attention on visual prototype for few-shot learning. In: WACV, pp. 1056–1066 (2022)
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, C., Cai, Y., Lin, G., Shen, C.: DeepEMD: few-shot image classification with differentiable earth mover’s distance and structured classifiers. In: CVPR, pp. 12203–12213 (2020)
Zhang, H., Koniusz, P., Jian, S., Li, H., Torr, P.H.: Rethinking class relations: absolute-relative supervised and unsupervised few-shot learning. In: CVPR, pp. 9432–9441 (2021)
Acknowledgement
This work was supported by Institute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government(MSIT) (No. 2019-0-00079, Artificial Intelligence Graduate School Program(Korea University) and No. 2022-0-00984, Development of Artificial Intelligence Technology for Personalized Plug-and-Play Explanation and Verification of Explanation and No.2019-0-01371, Development of brain-inspired AI with human-like intelligence).
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
Kim, TH., Nam, WJ., Lee, SW. (2023). Enhancing Robustness of Prototype with Attentive Information Guided Alignment in Few-Shot Classification. In: Kashima, H., Ide, T., Peng, WC. (eds) Advances in Knowledge Discovery and Data Mining. PAKDD 2023. Lecture Notes in Computer Science(), vol 13935. Springer, Cham. https://doi.org/10.1007/978-3-031-33374-3_15
Download citation
DOI: https://doi.org/10.1007/978-3-031-33374-3_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-33373-6
Online ISBN: 978-3-031-33374-3
eBook Packages: Computer ScienceComputer Science (R0)