Abstract
In this paper, we mainly focus on the problem of how to learn additional feature representations for few-shot image classification through pretext tasks (e.g., rotation or color permutation and so on). This additional knowledge generated by pretext tasks can further improve the performance of few-shot learning (FSL) as it differs from human-annotated supervision (i.e., class labels of FSL tasks). To solve this problem, we present a plug-in Hierarchical Tree Structure-aware (HTS) method, which not only learns the relationship of FSL and pretext tasks, but more importantly, can adaptively select and aggregate feature representations generated by pretext tasks to maximize the performance of FSL tasks. A hierarchical tree constructing component and a gated selection aggregating component is introduced to construct the tree structure and find richer transferable knowledge that can rapidly adapt to novel classes with a few labeled images. Extensive experiments show that our HTS can significantly enhance multiple few-shot methods to achieve new state-of-the-art performance on four benchmark datasets. The code is available at: https://github.com/remiMZ/HTS-ECCV22.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Note that our method mainly focuses on how to adaptively learn the knowledge of pretext tasks and improve the performance of few-shot image classification.
- 2.
During training, for a 5-way 1-/5-shot setting, one episode time is 0.45/0.54 s (0.39/0.50 s for baseline) with 75 query images over 500 randomly sampled episodes.
References
An, Y., Xue, H., Zhao, X., Zhang, L.: Conditional self-supervised learning for few-shot classification. In: International Joint Conference on Artificial Intelligence, IJCAI (2021)
Bateni, P., Goyal, R., Masrani, V., Wood, F., Sigal, L.: Improved few-shot visual classification. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR, pp. 14481–14490 (2020)
Bertinetto, L., Henriques, J.F., Torr, P.H.S., Vedaldi, A.: Meta-learning with differentiable closed-form solvers. In: International Conference on Learning Representations, ICLR (2019)
Chen, W., Liu, Y., Kira, Z., Wang, Y.F., Huang, J.: A closer look at few-shot classification. In: International Conference on Learning Representations, ICLR (2019)
Chen, Z., Ge, J., Zhan, H., Huang, S., Wang, D.: Pareto self-supervised training for few-shot learning. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR (2021)
Cubuk, E.D., Zoph, B., Mané, D., Vasudevan, V., Le, Q.V.: AutoAugment: learning augmentation strategies from data. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR (2019)
Cui, W., Guo, Y.: Parameterless transductive feature re-representation for few-shot learning. In: International Conference on Machine Learning, ICML (2021)
Deng, J., Dong, W., Socher, R., Li, L., Li, K., Li, F.: ImageNet: a large-scale hierarchical image database. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR (2009)
Feng, Z., Xu, C., Tao, D.: Self-supervised representation learning by rotation feature decoupling. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR (2019)
Finn, C., Abbeel, P., Levine, S.: Model-agnostic meta-learning for fast adaptation of deep networks. In: International Conference on Machine Learning, ICML (2017)
Gidaris, S., Bursuc, A., Komodakis, N., Pérez, P., Cord, M.: Boosting few-shot visual learning with self-supervision. In: International Conference on Computer Vision, ICCV (2019)
Gidaris, S., Singh, P., Komodakis, N.: Unsupervised representation learning by predicting image rotations. In: International Conference on Learning Representations, ICLR (2018)
Hou, R., Chang, H., Ma, B., Shan, S., Chen, X.: Cross attention network for few-shot classification. In: Advances in Neural Information Processing Systems, NeurIPS (2019)
Kang, D., Kwon, H., Min, J., Cho, M.: Relational embedding for few-shot classification. In: International Conference on Computer Vision, ICCV (2021)
Laurens, V.D.M., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9, 2579–2605 (2008)
Lee, H., Hwang, S.J., Shin, J.: Self-supervised label augmentation via input transformations. In: International Conference on Machine Learning, ICML (2020)
Li, F., Fergus, R., Perona, P.: A bayesian approach to unsupervised one-shot learning of object categories. In: International Conference on Computer Vision, ICCV (2003)
Li, H., Eigen, D., Dodge, S., Zeiler, M., Wang, X.: Finding task-relevant features for few-shot learning by category traversal. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR (2019)
Li, W., Wang, L., Xu, J., Huo, J., Gao, Y., Luo, J.: Revisiting local descriptor based image-to-class measure for few-shot learning. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR (2019)
Li, W., Xu, J., Huo, J., Wang, L., Gao, Y., Luo, J.: Distribution consistency based covariance metric networks for few-shot learning. In: Association for the Advancement of Artificial Intelligence, AAAI (2019)
Li, Z., Zhou, F., Chen, F., Li, H.: Meta-SGD: learning to learn quickly for few shot learning. CoRR abs/1707.09835 (2017)
Liu, L., Hamilton, W.L., Long, G., Jiang, J., Larochelle, H.: A universal representation transformer layer for few-shot image classification. In: International Conference on Learning Representations, ICLR. OpenReview.net (2021)
Liu, L., Zhou, T., Long, G., Jiang, J., Zhang, C.: Learning to propagate for graph meta-learning. In: Advances in Neural Information Processing Systems, NeurIPS, pp. 1037–1048 (2019)
Liu, S., Davison, A.J., Johns, E.: Self-supervised generalisation with meta auxiliary learning. In: Advances in Neural Information Processing Systems, NeurIPS (2020)
Misra, I., van der Maaten, L.: Self-supervised learning of pretext-invariant representations. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR (2020)
Ni, R., Goldblum, M., Sharaf, A., Kong, K., Goldstein, T.: Data augmentation for meta-learning. In: International Conference on Machine Learning, ICML (2021)
Qiao, S., Liu, C., Shen, W., Yuille, A.L.: Few-shot image recognition by predicting parameters from activations. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR (2018)
Ravichandran, A., Bhotika, R., Soatto, S.: Few-shot learning with embedded class models and shot-free meta training. In: International Conference on Computer Vision, ICCV (2019)
Ren, M., et al.: Meta-learning for semi-supervised few-shot classification. In: International Conference on Learning Representations, ICLR (2018)
Requeima, J., Gordon, J., Bronskill, J., Nowozin, S., Turner, R.E.: Fast and flexible multi-task classification using conditional neural adaptive processes. In: Advances in Neural Information Processing Systems, NeurIPS, pp. 7957–7968 (2019)
Rusu, A.A., et al.: Meta-learning with latent embedding optimization. In: International Conference on Learning Representations, ICLR (2019)
Satorras, V.G., Estrach, J.B.: Few-shot learning with graph neural networks. In: International Conference on Learning Representations, ICLR (2018)
Snell, J., Swersky, K., Zemel, R.S.: Prototypical networks for few-shot learning. In: Advances in Neural Information Processing Systems, NeurIPS (2017)
Su, J.-C., Maji, S., Hariharan, B.: When does self-supervision improve few-shot learning? In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12352, pp. 645–666. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58571-6_38
Sung, F., Yang, Y., Zhang, L., Xiang, T., Torr, P.H.S., Hospedales, T.M.: Learning to compare: relation network for few-shot learning. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR (2018)
Tai, K.S., Socher, R., Manning, C.D.: Improved semantic representations from tree-structured long short-term memory networks. In: Association for Computational Linguistics, ACL (2015)
Tian, Y., Wang, Y., Krishnan, D., Tenenbaum, J.B., Isola, P.: Rethinking few-shot image classification: a good embedding is all you need? In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12359, pp. 266–282. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58568-6_16
Vinyals, O., Blundell, C., Lillicrap, T., Kavukcuoglu, K., Wierstra, D.: Matching networks for one shot learning. In: Advances in Neural Information Processing Systems, NeurIPS (2016)
Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The Caltech-UCSD Birds-200-2011 Dataset. California Institute of Technology (CNS-TR-2011-001) (2011)
Yao, H., Wei, Y., Huang, J., Li, Z.: Hierarchically structured meta-learning. In: International Conference on Machine Learning, ICML. Proceedings of Machine Learning Research, vol. 97, pp. 7045–7054. PMLR (2019)
Ye, H., Hu, H., Zhan, D., Sha, F.: Few-shot learning via embedding adaptation with set-to-set functions. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR (2020)
Zhang, C., Cai, Y., Lin, G., Shen, C.: DeepEMD: few-shot image classification with differentiable earth mover’s distance and structured classifiers. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR, pp. 12200–12210 (2020)
Zhang, M., Zhang, J., Lu, Z., Xiang, T., Ding, M., Huang, S.: IEPT: instance-level and episode-level pretext tasks for few-shot learning. In: International Conference on Learning Representations, ICLR (2020)
Zhang, M., Huang, S., Wang, D.: Domain generalized few-shot image classification via meta regularization network. In: ICASSP, pp. 3748–3752 (2022)
Zhang, M., Wang, D., Gai, S.: Knowledge distillation for model-agnostic meta-learning. In: European Conference on Artificial Intelligence, ECAI (2020)
Acknowledgments
This work was supported by the National Science and Technology Innovation 2030 - Major Project (Grant No. 2022ZD0208800), and NSFC General Program (Grant No. 62176215). We thank Dr. Zhitao Wang for helpful feedback and discussions.
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
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Zhang, M., Huang, S., Li, W., Wang, D. (2022). Tree Structure-Aware Few-Shot Image Classification via Hierarchical Aggregation. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds) Computer Vision – ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, vol 13680. Springer, Cham. https://doi.org/10.1007/978-3-031-20044-1_26
Download citation
DOI: https://doi.org/10.1007/978-3-031-20044-1_26
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-20043-4
Online ISBN: 978-3-031-20044-1
eBook Packages: Computer ScienceComputer Science (R0)