Skip to main content

Kernel Relative-prototype Spectral Filtering for Few-Shot Learning

  • Conference paper
  • First Online:
Computer Vision – ECCV 2022 (ECCV 2022)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 13680))

Included in the following conference series:

Abstract

Few-shot learning performs classification tasks and regression tasks on scarce samples. As one of the most representative few-shot learning models, Prototypical Network represents each class as sample average, or a prototype, and measures the similarity of samples and prototypes by Euclidean distance. In this paper, we propose a framework of spectral filtering (shrinkage) for measuring the difference between query samples and prototypes, or namely the relative prototypes, in a reproducing kernel Hilbert space (RKHS). In this framework, we further propose a method utilizing Tikhonov regularization as the filter function for few-shot classification. We conduct several experiments to verify our method utilizing different kernels based on the miniImageNet dataset, tiered-ImageNet dataset and CIFAR-FS dataset. The experimental results show that the proposed model can perform the state-of-the-art. In addition, the experimental results show that the proposed shrinkage method can boost the performance. Source code is available at https://github.com/zhangtao2022/DSFN.

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

Access this chapter

Subscribe and save

Springer+ Basic
EUR 32.99 /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
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Alman, J., Williams, V.V.: A refined laser method and faster matrix multiplication. In: Proceedings of the 2021 ACM-SIAM Symposium on Discrete Algorithms (SODA), pp. 522–539. SIAM (2021)

    Google Scholar 

  2. Andrychowicz, M., et al.: Learning to learn by gradient descent by gradient descent. In: Advances in Neural Information Processing Systems, pp. 3981–3989 (2016)

    Google Scholar 

  3. Bateni, P., Goyal, R., Masrani, V., Wood, F., Sigal, L.: Improved few-shot visual classification. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 14493–14502 (2020)

    Google Scholar 

  4. Bertinetto, L., Henriques, J.F., Torr, P.H., Vedaldi, A.: Meta-learning with differentiable closed-form solvers. arXiv preprint arXiv:1805.08136 (2018)

  5. Chen, J., Zhan, L., Wu, X., Chung, F.: Variational metric scaling for metric-based meta-learning. In: The Thirty-Fourth AAAI Conference on Artificial Intelligence, pp. 3478–3485 (2020)

    Google Scholar 

  6. Chen, W.Y., Liu, Y.C., Kira, Z., Wang, Y.C.F., Huang, J.B.: A closer look at few-shot classification. arXiv preprint arXiv:1904.04232 (2019)

  7. Chonavel, T., Champagne, B., Riou, C.: Fast adaptive eigenvalue decomposition: a maximum likelihood approach. Signal Process. 83(2), 307–324 (2003)

    Article  Google Scholar 

  8. Fang, P., Harandi, M., Petersson, L.: Kernel methods in hyperbolic spaces. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 10665–10674 (2021)

    Google Scholar 

  9. Feifei, L., Fergus, R., Perona, P.: One-shot learning of object categories. IEEE Trans. Pattern Anal. Mach. Intell. 28(4), 594–611 (2006)

    Article  Google Scholar 

  10. Finn, C., Abbeel, P., Levine, S.: Model-agnostic meta-learning for fast adaptation of deep networks. In: Proceedings of the 34th International Conference on Machine Learning, p. 1126–1135. JMLR. org. (2017)

    Google Scholar 

  11. Fort, S.: Gaussian prototypical networks for few-shot learning on omniglot. arXiv preprint arXiv:1708.02735 (2017)

  12. Gao, T., Han, X., Liu, Z., Sun, M.: Hybrid attention-based prototypical networks for noisy few-shot relation classification. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 6407–6414 (2019)

    Google Scholar 

  13. Gidaris, S., Komodakis, N.: Dynamic few-shot visual learning without forgetting. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4367–4375 (2018)

    Google Scholar 

  14. Gidaris, S., Komodakis, N.: Generating classification weights with GNN denoising autoencoders for few-shot learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 21–30 (2019)

    Google Scholar 

  15. Kang, D., Kwon, H., Min, J., Cho, M.: Relational embedding for few-shot classification. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 8822–8833 (2021)

    Google Scholar 

  16. Khrulkov, V., Mirvakhabova, L., Ustinova, E., Oseledets, I., Lempitsky, V.: Hyperbolic image embeddings. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6418–6428 (2020)

    Google Scholar 

  17. Koch, G., Zemel, R., Salakhutdinov, R., et al.: Siamese neural networks for one-shot image recognition. In: ICML Deep Learning Workshop, vol. 2 (2015)

    Google Scholar 

  18. Krizhevsky, A., Hinton, G., et al.: Learning multiple layers of features from tiny images (2009)

    Google Scholar 

  19. Lake, B.M., Salakhutdinov, R., Tenenbaum, J.B.: Human-level concept learning through probabilistic program induction. Science 350(6266), 1332–1338 (2015)

    Article  MathSciNet  Google Scholar 

  20. Lee, K., Maji, S., Ravichandran, A., Soatto, S.: Meta-learning with differentiable convex optimization. 10657–10665. arXiv:1904.03758 (2019)

  21. Li, H., Eigen, D., Dodge, S., Zeiler, M., Wang, X.: Finding task-relevant features for few-shot learning by category traversal. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1–10 (2019)

    Google Scholar 

  22. Liu, J., Song, L., Qin, Y.: Prototype rectification for few-shot learning. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 741–756. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58452-8_43

    Chapter  Google Scholar 

  23. Mangla, P., Kumari, N., Sinha, A., Singh, M., Krishnamurthy, B., Balasubramanian, V.N.: 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)

    Google Scholar 

  24. Mishra, N., Rohaninejad, M., Chen, X., Abbeel, P.: A simple neural attentive meta-learner. In: 6th International Conference on Learning Representations (2018)

    Google Scholar 

  25. Muandet, K., Fukumizu, K., Sriperumbudur, B., Gretton, A., Scholkopf, B.: Kernel mean estimation and stein effect. In: International Conference on Machine Learning, pp. 10–18 (2014)

    Google Scholar 

  26. Muandet, K., Fukumizu, K., Sriperumbudur, B., Scholkopf, B.: Kernel mean embedding of distributions: a review and beyond. arXiv preprint arXiv:1605.09522 (2016)

  27. Muandet, K., Sriperumbudur, B., Fukumizu, K., Gretton, A., Scholkopf, B.: Kernel mean shrinkage estimators. J. Mach. Learn. Res. 17, 1–41 (2016)

    MathSciNet  MATH  Google Scholar 

  28. Muandet, K., Sriperumbudur, B., Scholkopf, B.: Kernel mean estimation via spectral filtering. arXiv preprint arXiv:1411.0900 (2014)

  29. Munkhdalai, T., Yu, H.: Meta networks. In: Proceedings of the 34th International Conference on Machine Learning, pp. 2554–2563 (2017)

    Google Scholar 

  30. Munkhdalai, T., Yuan, X., Mehri, S., Trischler, A.: Rapid adaptation with conditionally shifted neurons. In: International Conference on Machine Learning, pp. 3664–3673 (2018)

    Google Scholar 

  31. Nichol, A., Achiam, J., Schulman, J.: On first-order meta-learning algorithms. arXiv preprint arXiv:1803.02999 (2018)

  32. Oreshkin, B.N., Lopez, P.R., Lacoste, A.: Tadam: task dependent adaptive metric for improved few-shot learning. In: Advances in Neural Information Processing Systems, pp. 721–731 (2018)

    Google Scholar 

  33. Pahde, F., Puscas, M., Klein, T., Nabi, M.: Multimodal prototypical networks for few-shot learning. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 2644–2653 (2021)

    Google Scholar 

  34. Paszke, A., et al.: Automatic differentiation in pytorch (2017)

    Google Scholar 

  35. Ravi, S., Larochelle, H.: Optimization as a model for few-shot learning (2016)

    Google Scholar 

  36. Ren, M., et al.: Meta-learning for semi-supervised few-shot classification. arXiv preprint arXiv:1803.00676 (2018)

  37. Rodríguez, P., Laradji, I., Drouin, A., Lacoste, A.: Embedding propagation: smoother manifold for few-shot classification. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12371, pp. 121–138. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58574-7_8

    Chapter  Google Scholar 

  38. Rusu, A.A., et al.: Meta-learning with latent embedding optimization. arXiv preprint arXiv:1807.05960 (2018)

  39. Scholkopf, B., Smola, A., Muller, K.R.: Nonlinear component analysis as a kernel eigenvalue problem. Neural Comput. 10(5), 1299–1319 (1998)

    Article  Google Scholar 

  40. Simon, C., Koniusz, P., Nock, R., Harandi, M.: Adaptive subspaces for few-shot learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4136–4145 (2020)

    Google Scholar 

  41. Snell, J., Swersky, K., Zemel, R.S.: Prototypical networks for few-shot learning. In: Advances in Neural Information Processing Systems, pp. 4077–4087 (2017)

    Google Scholar 

  42. 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: 2018 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1199–1208 (2018)

    Google Scholar 

  43. Vanschoren, J.: Meta-learning: a survey. arXiv:1810.03548 (2018)

  44. Vinyals, O., Blundell, C., Lillicrap, T., Kavukcuoglu, K., Wierstra, D.: Matching networks for one shot learning. In: Advances in Neural Information Processing Systems, pp. 3637–3645 (2016)

    Google Scholar 

  45. Xing, C., Rostamzadeh, N., Oreshkin, B., Pinheiro, P.O.: Adaptive cross-modal few-shot learning. In: Advanced Neural Information Processing System, vol. 32, pp. 4847–4857 (2019)

    Google Scholar 

  46. Ye, H.J., Hu, H., Zhan, D.C., Sha, F.: 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)

    Google Scholar 

  47. Zhang, H., Koniusz, P.: Zero-shot kernel learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7670–7679 (2018)

    Google Scholar 

  48. Ziko, I., Dolz, J., Granger, E., Ayed, I.B.: Laplacian regularized few-shot learning. In: International Conference on Machine Learning, pp. 11660–11670 (2020)

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Tao Zhang .

Editor information

Editors and Affiliations

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 219 KB)

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

Zhang, T., Huang, W. (2022). Kernel Relative-prototype Spectral Filtering for Few-Shot Learning. 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_31

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-20044-1_31

  • 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)

Publish with us

Policies and ethics