Abstract
Few-shot Learning (FSL) aims to learn a classifier that can be easily adapted to recognize novel classes with only a few labeled examples. Recently, some works about FSL have yielded promising classification performance, where the image-level feature is used to calculate the similarity among samples for classification. However, the image-level feature ignores abundant fine-grained and structural information of objects that could be transferable and consistent between seen and unseen classes. How can humans easily identify novel classes with several samples? Some studies from cognitive science argue that humans recognize novel categories based on primitives. Although base and novel categories are non-overlapping, they share some primitives in common. Inspired by above research, we propose a Primitive Mining and Reasoning Network (PMRN) to learn primitive-aware representations based on metric-based FSL model. Concretely, we first add Self-supervision Jigsaw task (SSJ) for feature extractor parallelly, guiding the model encoding visual pattern corresponding to object parts into feature channels. Moreover, to mine discriminative representations, an Adaptive Channel Grouping (ACG) method is applied to cluster and weight spatially and semantically related visual patterns to generate a set of visual primitives. To further enhance the discriminability and transferability of primitives, we propose a visual primitive Correlation Reasoning Network (CRN) based on Graph Convolutional network to learn abundant structural information and internal correlation among primitives. Finally, a primitive-level metric is conducted for classification in a meta-task based on episodic training strategy. Extensive experiments show that our method achieves state-of-the-art results on miniImageNet and Caltech-UCSD Birds.
(a) The preprint of this paper: Yang J, Niu Y, Xie X, Shi G. Learning Primitive-aware Discriminative Representations for Few-shot Learning[J]. arXiv preprint arXiv:2208.09717, 2022. https://arxiv.org/abs/2208.09717.
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
Finn, C., Abbeel, P., Levine, S.: Model-agnostic meta-learning for fast adaptation of deep net-works. In: International Conference on Machine Learning. PMLR, pp. 1126–1135 (2017)
Vinyals, O., Blundell, C., Lillicrap, T., et al.: Matching networks for one shot learning. In: Advances in Neural Information Processing Systems, vol. 29 (2016)
Snell, J., Swersky, K., Zemel, R.: Prototypical networks for few-shot learning. In: Advances in Neural Information Processing Systems, vol. 30 (2017)
Sung, F., Yang, Y., Zhang, L., et al.: 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)
Li, W., Wang, L., Xu, J., et al.: Revisiting local descriptor based image-to-class measure for few-shot learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7260–7268 (2019)
Zhang, C., Cai, Y., Lin, G., et al.: DeepEMD: differentiable earth mover’s distance for few-shot learning. IEEE Trans. Pattern Anal. Mach. Intell. (2022)
Dong, C., Li, W., Huo, J., et al.: Learning task-aware local representations for few-shot learning. In: Proceedings of the Twenty-Ninth International Conference on International Joint Conferences on Artificial Intelligence, pp. 716–722 (2021)
Liu, Y., Zhang, W., Xiang, C., et al.: Learning to affiliate: mutual centralized learning for few-shot classification. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 14411–14420 (2022)
Zhou, B., Khosla, A., Lapedriza, A., et al.: Learning deep features for discriminative localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2921–2929 (2016)
Wu, J., Zhang, T., Zhang, Y., et al.: Task-aware part mining network for few-shot learning. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 8433–8442 (2021)
Ashok, A., Aekula, H.: When does self-supervision improve few-shot learning?-A reproducibility report. In: ML Reproducibility Challenge (Fall Edition) (2021)
Zheng, H., Fu, J., Mei, T., et al.: Learning multi-attention convolutional neural network for fine-grained image recognition. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5209–5217 (2017)
He, K., Zhang, X., Ren, S., et al.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv pre-print arXiv:1412.6980 (2014)
Ye, H.J., Hu, H., Zhan, D.C., et al.: Few-shot learning via embedding adaptation with set-to-set functions. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 8808–8817 (2020)
Hou, R., Chang, H., Ma, B., et al.: Cross attention network for few-shot classification. In: Advances in Neural Information Processing Systems, 32 (2019)
Wertheimer, D., Tang, L., Hariharan, B.: Few-shot classification with feature map reconstruction networks. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 8012–8021 (2021)
Simon, C., Koniusz, P., Nock, R., et al.: Adaptive subspaces for few-shot learn-ing. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4136–4145 (2020)
Li, H., Eigen, D., Dodge, S., et al.: Finding task-relevant features for few-shot learning by cate-gory traversal. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1–10 (2019)
He, Y., Liang, W., Zhao, D., et al.: Attribute surrogates learning and spectral tokens pooling in transformers for few-shot learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9119–9129 (2022)
Bendou, Y., Hu, Y., Lafargue, R., et al.: Easy—ensemble augmented-shot-Y-shaped learning: state-of-the-art few-shot classification with simple components. J. Imaging 8(7), 179 (2022)
Antoniou, A., Storkey, A.J.: Learning to learn by self-critique. In: Advances in Neural Information Processing Systems, 32 (2019)
Mangla, P., Kumari, N., Sinha, A., et al.: Charting the right manifold: manifold mixup for few-shot learning. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 2218–2227 (2020)
Zhou, F., Wu, B., Li, Z.: Deep meta learning: learning to learn in the concept space. arXiv preprint arXiv:1802.03596 (2018)
Hu, P., Sun, X., Saenko, K., et al.: Weakly-supervised compositional featureaggregation for few-shot recognition. arXiv preprint arXiv:1906.04833 (2019)
Santoro, A., Bartunov, S., Botvinick, M., et al.: Meta-learning with memory-augmented neural networks. In: International Conference on Machine Learning. PMLR, pp. 1842–1850 (2016)
Koch, G., Zemel, R., Salakhutdinov, R.: Siamese neural networks for one-shot image recognition. In: ICML Deep Learning Workshop, vol. 2(1) (2015)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. Commun. ACM 60(6), 84–90 (2017)
Welinder, P., et al.: Caltechucsd birds 200 (2010)
Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vision 115(3), 211–252 (2015). https://doi.org/10.1007/s11263-015-0816-y
Acknowledgements
This research was financially and technically supported by Guangzhou Key Research and Development Program (202206030003) and the Guangzhou Key Laboratory of Scene Understanding and Intelligent Interaction (No. 202201000001).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Yang, J., Niu, Y., Xie, X., Shi, G. (2024). Learning Primitive-Aware Discriminative Representations for Few-Shot Learning. In: Luo, B., Cheng, L., Wu, ZG., Li, H., Li, C. (eds) Neural Information Processing. ICONIP 2023. Lecture Notes in Computer Science, vol 14448. Springer, Singapore. https://doi.org/10.1007/978-981-99-8082-6_11
Download citation
DOI: https://doi.org/10.1007/978-981-99-8082-6_11
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-8081-9
Online ISBN: 978-981-99-8082-6
eBook Packages: Computer ScienceComputer Science (R0)