Skip to main content

Multi-level Metric Learning for Few-Shot Image Recognition

  • Conference paper
  • First Online:
Artificial Neural Networks and Machine Learning – ICANN 2022 (ICANN 2022)

Abstract

Few-shot learning devotes to training a model on a few samples. Most of these approaches learn a model based on a pixel-level or global-level feature representation. However, using global features may lose local information, and using pixel-level features may lose the contextual semantics of the image. Moreover, such works can only measure their relations on a single level, which is not comprehensive and effective. And if query images can simultaneously be well classified via three distinct level similarity metrics, the query images within a class can be more tightly distributed in a smaller feature space, generating more discriminative feature maps. Motivated by this, we propose a novel Part-level Embedding Adaptation with Graph (PEAG) method to generate task-specific features. Moreover, a Multi-level Metric Learning (MML) method is proposed, which not only calculates the part-level similarity but also considers the similarity of pixel-level and global-level metrics. Extensive experiments on popular few-shot image recognition datasets prove the effectiveness of our method compared with the state-of-the-art methods. Our code is available at: https://github.com/chenhaoxing/M2L.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Bertinetto, L., Henriques, J.F., Torr, P.H.S., Vedaldi, A.: Meta-learning with differentiable closed-form solvers. In: ICLR (2019)

    Google Scholar 

  2. Chen, H., Li, H., Li, Y., Chen, C.: Multi-scale adaptive task attention network for few-shot learning. In: ICPR (2022)

    Google Scholar 

  3. Chen, S., et al.: MSDN: mutually semantic distillation network for zero-shot learning. In: CVPR (2022)

    Google Scholar 

  4. Chen, Y., Liu, Z., Xu, H., Darrell, T., Wang, X.: Meta-baseline: exploring simple meta-learning for few-shot learning. In: ICCV, pp. 9042–9051 (2021)

    Google Scholar 

  5. Chen, Z., Ge, J., Zhan, H., Huang, S., Wang, D.: Pareto self-supervised training for few-shot learning (2021)

    Google Scholar 

  6. Deng, J., Dong, W., Socher, R., Li, L., Li, K., Li, F.: ImageNet: a large-scale hierarchical image database. In: CVPR, pp. 248–255 (2009)

    Google Scholar 

  7. Dhillon, G.S., Chaudhari, P., Ravichandran, A., Soatto, S.: A baseline for few-shot image classification. In: ICLR (2020)

    Google Scholar 

  8. Dong, B., Zhou, P., Yan, S., Zuo, W.: Self-promoted supervision for few-shot transformer

    Google Scholar 

  9. Finn, C., Abbeel, P., Levine, S.: Model-agnostic meta-learning for fast adaptation of deep networks. In: ICML, vol. 70, pp. 1126–1135 (2017)

    Google Scholar 

  10. Guo, Y., Cheung, N.: Attentive weights generation for few shot learning via information maximization. In: CVPR, pp. 13496–13505 (2020)

    Google Scholar 

  11. Hou, R., Chang, H., Ma, B., Shan, S., Chen, X.: Cross attention network for few-shot classification. In: NeurIPS, pp. 4005–4016 (2019)

    Google Scholar 

  12. Kim, J., Kim, H., Kim, G.: Model-agnostic boundary-adversarial sampling for test-time generalization in few-shot learning. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 599–617. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58452-8_35

    Chapter  Google Scholar 

  13. Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: ICLR (2017)

    Google Scholar 

  14. Koch, G., Zemel, R., Salakhutdinov, R.: Siamese neural networks for one-shot image recognition. In: ICML Workshops, vol. 2 (2015)

    Google Scholar 

  15. Lee, K., Maji, S., Ravichandran, A., Soatto, S.: Meta-learning with differentiable convex optimization. In: CVPR, pp. 10657–10665 (2019)

    Google Scholar 

  16. Li, J., Xiong, C., Hoi, S.C.H.: Comatch: semi-supervised learning with contrastive graph regularization. In: ICCV, pp. 9455–9464 (2021)

    Google Scholar 

  17. 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: CVPR, pp. 7260–7268 (2019)

    Google Scholar 

  18. Li, W., Xu, J., Huo, J., Wang, L., Gao, Y., Luo, J.: Distribution consistency based covariance metric networks for few-shot learning. In: AAAI, pp. 8642–8649 (2019)

    Google Scholar 

  19. Lu, S., Ye, H., Zhan, D.: Tailoring embedding function to heterogeneous few-shot tasks by global and local feature adaptors. In: AAAI, pp. 8776–8783 (2021)

    Google Scholar 

  20. Oreshkin, B.N., López, P.R., Lacoste, A.: TADAM: task dependent adaptive metric for improved few-shot learning. In: NeurIPS, pp. 719–729 (2018)

    Google Scholar 

  21. Qiao, L., Shi, Y., Li, J., Tian, Y., Huang, T., Wang, Y.: Transductive episodic-wise adaptive metric for few-shot learning. In: ICCV, pp. 3602–3611 (2019)

    Google Scholar 

  22. Ravichandran, A., Bhotika, R., Soatto, S.: Few-shot learning with embedded class models and shot-free meta training. In: ICCV, pp. 331–339 (2019)

    Google Scholar 

  23. Ren, M., et al.: Meta-learning for semi-supervised few-shot classification. In: ICLR (2018)

    Google Scholar 

  24. Simon, C., Koniusz, P., Nock, R., Harandi, M.: Adaptive subspaces for few-shot learning. In: CVPR, pp. 4135–4144 (2020)

    Google Scholar 

  25. Snell, J., Swersky, K., Zemel, R.S.: Prototypical networks for few-shot learning. In: NeurIPS, pp. 4077–4087 (2017)

    Google Scholar 

  26. Sun, Q., Liu, Y., Chua, T., Schiele, B.: Meta-transfer learning for few-shot learning. In: CVPR, pp. 403–412 (2019)

    Google Scholar 

  27. 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: CVPR, pp. 1199–1208 (2018)

    Google Scholar 

  28. Vinyals, O., Blundell, C., Lillicrap, T., Kavukcuoglu, K., Wierstra, D.: Matching networks for one shot learning. In: NeurIPS, pp. 3630–3638 (2016)

    Google Scholar 

  29. Wang, Y., Khan, S., Gonzalez-Garcia, A., van de Weijer, J., Khan, F.S.: Semi-supervised learning for few-shot image-to-image translation. In: CVPR, pp. 4452–4461 (2020)

    Google Scholar 

  30. Wu, J., Zhang, T., Zha, Z., Luo, J., Zhang, Y., Wu, F.: Self-supervised domain-aware generative network for generalized zero-shot learning. In: CVPR, pp. 12764–12773 (2020)

    Google Scholar 

  31. Xing, C., Rostamzadeh, N., Oreshkin, B.N., Pinheiro, P.O.: Adaptive cross-modal few-shot learning. In: NeurIPS, pp. 4848–4858 (2019)

    Google Scholar 

  32. Xu, M., et al.: End-to-end semi-supervised object detection with soft teacher. In: ICCV, pp. 3040–3049 (2021)

    Google Scholar 

  33. 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)

    Google Scholar 

  34. Yoon, S.W., Seo, J., Moon, J.: TapNet: neural network augmented with task-adaptive projection for few-shot learning. In: ICML, vol. 97, pp. 7115–7123 (2019)

    Google Scholar 

  35. Yu, Y., Ji, Z., Han, J., Zhang, Z.: Episode-based prototype generating network for zero-shot learning. In: CVPR, pp. 14032–14041 (2020)

    Google Scholar 

  36. Zhang, C., Ding, H., Lin, G., Li, R., Wang, C., Shen, C.: Meta navigator: search for a good adaptation policy for few-shot learning. In: ICCV, pp. 9415–9424 (2021)

    Google Scholar 

  37. Zhang, X., Meng, D., Gouk, H., Hospedales, T.M.: Shallow Bayesian meta learning for real-world few-shot recognition. In: ICCV, pp. 631–640 (2021)

    Google Scholar 

Download references

Acknolewdgement

This work was partially supported by the National Natural Science Foundation of China (Nos. 62176116, 62073160, 71732003), and the Natural Science Foundation of the Jiangsu Higher Education Institutions of China, No. 20KJA520006.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Huaxiong Li .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Chen, H., Li, H., Li, Y., Chen, C. (2022). Multi-level Metric Learning for Few-Shot Image Recognition. In: Pimenidis, E., Angelov, P., Jayne, C., Papaleonidas, A., Aydin, M. (eds) Artificial Neural Networks and Machine Learning – ICANN 2022. ICANN 2022. Lecture Notes in Computer Science, vol 13529. Springer, Cham. https://doi.org/10.1007/978-3-031-15919-0_21

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-15919-0_21

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-15918-3

  • Online ISBN: 978-3-031-15919-0

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics