Skip to main content
Springer Nature Link
Log in

Few-Shot Classification with Contrastive 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:

  • 4085 Accesses

Abstract

A two-stage training paradigm consisting of sequential pre-training and meta-training stages has been widely used in current few-shot learning (FSL) research. Many of these methods use self-supervised learning and contrastive learning to achieve new state-of-the-art results. However, the potential of contrastive learning in both stages of FSL training paradigm is still not fully exploited. In this paper, we propose a novel contrastive learning-based framework that seamlessly integrates contrastive learning into both stages to improve the performance of few-shot classification. In the pre-training stage, we propose a self-supervised contrastive loss in the forms of feature vector vs. feature map and feature map vs. feature map, which uses global and local information to learn good initial representations. In the meta-training stage, we propose a cross-view episodic training mechanism to perform the nearest centroid classification on two different views of the same episode and adopt a distance-scaled contrastive loss based on them. These two strategies force the model to overcome the bias between views and promote the transferability of representations. Extensive experiments on three benchmark datasets demonstrate that our method achieves competitive results.

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

Access this chapter

Log in via an institution

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. Bachman, P., Hjelm, R.D., Buchwalter, W.: Learning representations by maximizing mutual information across views. In: NIPS, pp. 15509–15519 (2019)

    Google Scholar 

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

    Google Scholar 

  3. Chen, T., Kornblith, S., Norouzi, M., Hinton, G.E.: A simple framework for contrastive learning of visual representations. In: ICML, pp. 1597–1607 (2020)

    Google Scholar 

  4. Chen, T., Kornblith, S., Swersky, K., Norouzi, M., Hinton, G.E.: Big self-supervised models are strong semi-supervised learners. In: NIPS, pp. 22243–22255 (2020)

    Google Scholar 

  5. Chen, W., Liu, Y., Kira, Z., Wang, Y.F., Huang, J.: A closer look at few-shot classification. In: ICLR (2019)

    Google Scholar 

  6. Chen, Y., Liu, Z., Xu, H., Darrell, T., Wang, X.: Meta-baseline: exploring simple meta-learning for few-shot learning. In: ICCV, pp. 9062–9071 (2021)

    Google Scholar 

  7. Chen, Z., Ge, J., Zhan, H., Huang, S., Wang, D.: Pareto self-supervised training for few-shot learning. In: CVPR, pp. 13663–13672 (2021)

    Google Scholar 

  8. Cubuk, E.D., Zoph, B., Mané, D., Vasudevan, V., Le, Q.V.: Autoaugment: learning augmentation strategies from data. In: CVPR, pp. 113–123 (2019)

    Google Scholar 

  9. Doersch, C., Gupta, A., Zisserman, A.: Crosstransformers: spatially-aware few-shot transfer. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M., Lin, H. (eds.) NIPS, pp. 21981–21993 (2020)

    Google Scholar 

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

    Google Scholar 

  11. Gidaris, S., Bursuc, A., Komodakis, N., Pérez, P., Cord, M.: Boosting few-shot visual learning with self-supervision. In: ICCV, pp. 8058–8067 (2019)

    Google Scholar 

  12. Gidaris, S., Komodakis, N.: Generating classification weights with GNN denoising autoencoders for few-shot learning. In: CVPR, pp. 21–30 (2019)

    Google Scholar 

  13. Gidaris, S., Singh, P., Komodakis, N.: Unsupervised representation learning by predicting image rotations. In: ICLR (2018)

    Google Scholar 

  14. He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.B.: Momentum contrast for unsupervised visual representation learning. In: CVPR, pp. 9726–9735 (2020)

    Google Scholar 

  15. He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770–778 (2016)

    Google Scholar 

  16. Hjelm, R.D., et al.: Learning deep representations by mutual information estimation and maximization. In: ICLR (2019)

    Google Scholar 

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

    Google Scholar 

  18. Kang, D., Kwon, H., Min, J., Cho, M.: Relational embedding for few-shot classification. In: ICCV, pp. 8822–8833 (2021)

    Google Scholar 

  19. Khosla, P., et al.: Supervised contrastive learning. In: NIPS, pp. 18661–18673 (2020)

    Google Scholar 

  20. 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 

  21. Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: NIPS, pp. 1106–1114 (2012)

    Google Scholar 

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

    Google Scholar 

  23. 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 

  24. Li, Z., Zhou, F., Chen, F., Li, H.: Meta-sgd: learning to learn quickly for few shot learning. arXiv preprint arXiv:1707.09835 (2017)

  25. Liu, C., et al.: Learning a few-shot embedding model with contrastive learning. In: AAAI, pp. 8635–8643 (2021)

    Google Scholar 

  26. Ma, J., Xie, H., Han, G., Chang, S.F., Galstyan, A., Abd-Almageed, W.: Partner-assisted learning for few-shot image classification. In: ICCV, pp. 10573–10582 (2021)

    Google Scholar 

  27. Van der Maaten, L., Hinton, G.: Visualizing data using t-sne. JMLR 9(11), 2579–2605 (2008)

    MATH  Google Scholar 

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

  29. Noroozi, M., Favaro, P.: Unsupervised learning of visual representations by solving jigsaw puzzles. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9910, pp. 69–84. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46466-4_5

    Chapter  Google Scholar 

  30. Oord, A.V.D., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)

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

    Google Scholar 

  32. Ouali, Y., Hudelot, C., Tami, M.: Spatial contrastive learning for few-shot classification. In: ECML-PKDD, pp. 671–686 (2021)

    Google Scholar 

  33. Ravi, S., Larochelle, H.: Optimization as a model for few-shot learning. In: ICLR (2017)

    Google Scholar 

  34. 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 

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

    Google Scholar 

  36. Rusu, A.A., et al.: Meta-learning with latent embedding optimization. In: ICLR (2019)

    Google Scholar 

  37. Satorras, V.G., Estrach, J.B.: Few-shot learning with graph neural networks. In: ICLR (2018)

    Google Scholar 

  38. Shen, Z., Liu, Z., Qin, J., Savvides, M., Cheng, K.: Partial is better than all: revisiting fine-tuning strategy for few-shot learning. In: AAAI, pp. 9594–9602 (2021)

    Google Scholar 

  39. Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: ICLR (2015)

    Google Scholar 

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

    Google Scholar 

  41. 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

    Chapter  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: CVPR, pp. 1199–1208 (2018)

    Google Scholar 

  43. Tian, Y., Krishnan, D., Isola, P.: Contrastive multiview coding. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12356, pp. 776–794. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58621-8_45

    Chapter  Google Scholar 

  44. Tian, Y., Sun, C., Poole, B., Krishnan, D., Schmid, C., Isola, P.: What makes for good views for contrastive learning? In: NIPS, pp. 6827–6839 (2020)

    Google Scholar 

  45. 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

    Chapter  Google Scholar 

  46. Vaswani, A., et al.: Attention is all you need. In: NIPS, pp. 5998–6008 (2017)

    Google Scholar 

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

    Google Scholar 

  48. Wang, Y., Chao, W.L., Weinberger, K.Q., van der Maaten, L.: Simpleshot: revisiting nearest-neighbor classification for few-shot learning. arXiv preprint arXiv:1911.04623 (2019)

  49. Wu, J., Zhang, T., Zhang, Y., Wu, F.: Task-aware part mining network for few-shot learning. In: ICCV, pp. 8433–8442 (2021)

    Google Scholar 

  50. Wu, Z., Xiong, Y., Yu, S.X., Lin, D.: Unsupervised feature learning via non-parametric instance discrimination. In: CVPR, pp. 3733–3742 (2018)

    Google Scholar 

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

    Google Scholar 

  52. Xu, C., et al.: Learning dynamic alignment via meta-filter for few-shot learning. In: CVPR, pp. 5182–5191 (2021)

    Google Scholar 

  53. Xu, W., Xu, Y., Wang, H., Tu, Z.: Attentional constellation nets for few-shot learning. In: ICLR (2021)

    Google Scholar 

  54. Ye, H., Hu, H., Zhan, D., Sha, F.: Few-shot learning via embedding adaptation with set-to-set functions. In: CVPR, pp. 8805–8814 (2020)

    Google Scholar 

  55. 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. 12200–12210 (2020)

    Google Scholar 

  56. Zhou, Z., Qiu, X., Xie, J., Wu, J., Zhang, C.: Binocular mutual learning for improving few-shot classification. In: ICCV, pp. 8402–8411 (2021)

    Google Scholar 

Download references

Acknowledgement

This work are supported by: (i) National Natural Science Foundation of China (Grant No. 62072318 and No. 62172285); (ii) Natural Science Foundation of Guangdong Province of China (Grant No. 2021A1515012014); (iii) Science and Technology Planning Project of Shenzhen Municipality (Grant No. JCYJ20190808172007500).

Author information

Authors and Affiliations

  1. College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China

    Zhanyuan Yang & Yingying Zhu

  2. School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, China

    Jinghua Wang

Authors
  1. Zhanyuan Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jinghua Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yingying Zhu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Yingying Zhu .

Editor information

Editors and Affiliations

  1. Tel Aviv University, Tel Aviv, Israel

    Shai Avidan

  2. University College London, London, UK

    Gabriel Brostow

  3. Google AI, Accra, Ghana

    Moustapha Cissé

  4. University of Catania, Catania, Italy

    Giovanni Maria Farinella

  5. Facebook (United States), Menlo Park, CA, USA

    Tal Hassner

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 997 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

Yang, Z., Wang, J., Zhu, Y. (2022). Few-Shot Classification with Contrastive 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_17

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-20044-1_17

  • 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