Skip to main content
Springer Nature Link
Log in

Optimization model based on attention mechanism for few-shot image classification

  • Research
  • Published:
Machine Vision and Applications Aims and scope Submit manuscript

Abstract

Deep learning has emerged as the leading approach for pattern recognition, but its reliance on large labeled datasets poses challenges in real-world applications where obtaining annotated samples is difficult. Few-shot learning, inspired by human learning, enables fast adaptation to new concepts with limited examples. Optimization-based meta-learning has gained popularity as a few-shot learning method. However, it struggles with capturing long-range dependencies of gradients and has slow convergence rates, making it challenging to extract features from limited samples. To overcome these issues, we propose MLAL, an optimization model based on attention for few-shot learning. The model comprises two parts: the attention-LSTM meta-learner, which optimizes gradients hierarchically using the self-attention mechanism, and the cross-attention base-learner, which uses the cross-attention mechanism to cross-learn the common category features of support and query sets in a meta-task. Extensive experiments on two benchmark datasets show that MLAL achieves exceptional 1-shot and 5-shot classification accuracy on MiniImagenet and TiredImagenet. The codes for our proposed method are available at https://github.com/wflrz123/MLAL.

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

Access this article

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

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Algorithm 1
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

References

  1. He, K., Zhang, X., Ren, S., et al.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2016, 770–778 (2016). https://doi.org/10.1109/CVPR.2016.90

  2. Wang, L., Zhang, L., Qi, X., et al.: Deep attention-based imbalanced image classification. IEEE Trans. Neural Netw. Learn. Syst. 33(8), 3320–3330 (2022). https://doi.org/10.1109/TNNLS.2021.3051721

    Article  MathSciNet  Google Scholar 

  3. Liu, Z., Miao, Z., Zhan, X., et al.: Open long-tailed recognition in a dynamic world. IEEE Trans. Pattern Anal. Mach. Intell. (2022). https://doi.org/10.1109/TPAMI.2022.3200091

    Article  Google Scholar 

  4. Zhai, M.Y., Chen, L., Mori, G.: Hyper-Lifelong AN: scalable lifelong learning for image conditioned generation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR2021), pp. 2246–2255 (2021)

  5. Zhai, M., Chen, L., Tung, F., et al.: Lifelong GAN: continual learning for conditional image generation. In: IEEE/CVF International Conference on Computer Vision (ICCV) 2019, 2759–2768 (2019). https://doi.org/10.1109/ICCV.2019.00285

  6. Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: 34th Conference on Neural Information Processing Systems (NeurIPS 2020), Vancouver, Canada

  7. Vaswani, A., Shazeer, N., Parmar, N., et al.: Attention is all you need. In: 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA

  8. Zhang, Z., Wu, Y., Zhou, J., et al.: SG-net: syntax guided transformer for language representation. In: IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 44, no. 6, pp. 3285–3299, 1 June 2022, https://doi.org/10.1109/TPAMI.2020.3046683

  9. Lu, Y., Zhang, J., Zeng, J., et al.: Attention analysis and calibration for transformer in natural language generation. IEEE/ACM Trans. Audio Speech Lang. Process. 30, 1927–1938 (2022). https://doi.org/10.1109/TASLP.2022.3180678

    Article  Google Scholar 

  10. Wang, Y., Yao, Q., Kwok, J. T.: et al. Generalizing from a few examples: a survey on few-shot learning. In: ACM Computing Surveys, Volume 53, Issue 3, 2021, Article No. 63, pp 1–34. https://doi.org/10.1145/3386252

  11. Lai, N., Kan, M., Han, C., et al.: Learning to learn adaptive classifier-predictor for few-shot learning. IEEE Trans. Neural Netw. Learn. Syst. 32(8), 3458–3470 (2021). https://doi.org/10.1109/TNNLS.2020.3011526

    Article  Google Scholar 

  12. Snell, J., Swersky, K., Zemel, R.: Prototypical networks for few-shot learning. In: 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA

  13. Hospedales, T., Antoniou, A., Micaelli, P., et al.: Meta-learning in neural networks: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 44(9), 5149–5169 (2022). https://doi.org/10.1109/TPAMI.2021.3079209

  14. Tian, Y., Zhao, X., Huang, W.: Meta-learning approaches for learning-to-learn in deep learning: a survey. Neurocomputing 494(14), 203–223 (2022)

    Article  Google Scholar 

  15. Huisman, M., van Rijn, J.N., Plaat, A.: A survey of deep meta-learning. Artif. Intell. Rev. 54(6), 4483–4541 (2021). https://doi.org/10.1007/s10462-021-10004-4

    Article  Google Scholar 

  16. Andrychowicz, M., Denil, M., Gomez, S., et al.: Learning to learn by gradient descent by gradient descent. Adv. Neural. Inf. Process. Syst. 29, 3–17 (2016)

    Google Scholar 

  17. Hopfield, J.J.: Neural networks and physical systems with emergent collective computational abilities. Proc. Natl. Acad. Sci. USA 79(8), 2554–2558 (1982)

    Article  MathSciNet  Google Scholar 

  18. Ravi, S., Larochelle, H.: Optimization as a model for few-shot learning. In: The 5th International Conference on Learning Representations (ICLR 2017), Toulon, France, April 24–26 (2017)

  19. Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 735–1780 (1997)

    Article  Google Scholar 

  20. Dosovitskiy, A., Beyer, L., Kolesnikov, A., et al.: An image is worth 16\(\times \)16 words: transformers for image recognition at scale. In: The 9th International Conference on Learning Representations (ICLR 2021), Vienna, Austria (2021)

  21. Koch, G., Zemel, R., Salakhutdinov, R.: Siamese neural networks for one-shot image recognition. In: Proceedings of the 32nd International Conference on Machine Learning, Lille, France, 2015. JMLR: W &CP volume 37

  22. Vinyals, O., Blundell, C., Lillicrap, T., et al.: Matching networks for one shot learning. In: 30th Conference on Neural Information Processing Systems (NIPS 2016), Barcelona, Spain

  23. Snell, J., Swersky, K., Zemel, R.: Prototypical networks for few-shot learning. In: 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA

  24. 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)

  25. Peng, H.: A comprehensive overview and survey of recent advances in meta-learning. arxiv:2004.11149

  26. Gao, F., Luo, X., Yang, Z., et al.: Label smoothing and task-adaptive loss function based on prototype network for few-shot learning. Neural Netw. 156, 39–48 (2022)

    Article  Google Scholar 

  27. Blaes, S., Burwick, T.: Few-shot learning in deep networks through global prototyping. Neural Netw. 94, 159–172 (2017)

    Article  Google Scholar 

  28. Finn, C., Abbeel, P., Levine, S.: Model-agnostic meta-learning for fast adaptation of deep networks. In: International Conference on Machine Learning, 1126–1135 (2017)

  29. Nichol, A., Achiam, J., Schulman, J.: On first-order meta-learning algorithms. arxiv:1803.02999

  30. Fei, N., Lu, Z., Xiang, T., et al.: MELR: meta-learning via modeling episode-level relationships for few-shot learning. In: The 8th International Conference on Learning Representations (ICLR 2020), Virtual Conference, Formerly Addis Ababa Ethiopia, Apr 26th through May 1st (2020)

  31. Guo, M.H., Xu, T.X., Liu, J.J., et al.: Attention mechanisms in computer vision: a survey. Comput. Visual Media 8, 331–368 (2022). https://doi.org/10.1007/s41095-022-0271-y

    Article  Google Scholar 

  32. Lei, J., Zhu, X., Wang, Y.: BAT: block and token self-attention for speech emotion recognition. Neural Netw. 156, 67–80 (2022)

    Article  Google Scholar 

  33. Li, J., Wang, H., Wu, K., et al.: Cross-attention-map-based regularization for adversarial domain adaptation. Neural Netw. 145, 128–138 (2022)

    Article  Google Scholar 

  34. Hou, R., Chang, H., Ma, B., et al.: Cross attention network for few-shot classification. In: 33rd Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, Canada

  35. Qin, Z., Wang, H., Mawuli, C.B., et al.: Multi-instance attention network for few-shot learning. Inf. Sci. 611, 464–475 (2022)

    Article  Google Scholar 

  36. Wang, Y., Yan, J., Ye, X., et al.: Few-shot transfer learning with attention mechanism for high-voltage circuit breaker fault diagnosis. IEEE Trans. Ind. Appl. 58(3), 3353–3360 (2022). https://doi.org/10.1109/TIA.2022.3159617

  37. Lee, E., Huang, C.H., Lee, C.Y.: Few-shot and continual learning with attentive independent mechanisms. In: IEEE/CVF International Conference on Computer Vision (ICCV) 2021, 9435–9444 (2021). https://doi.org/10.1109/ICCV48922.2021.00932

  38. Liu, Y., Zhang, H., Yang, Y.: Few-shot image classification based on asymmetric convolution and attention mechanism. In: 2022 4th International Conference on Natural Language Processing (ICNLP), Xi’an, China, pp. 217–222 (2022)

  39. Afrasiyabi, A., Lalonde, J.F., Gagné, C.: Mixture-based feature space learning for few-shot image classification. In: 2021 IEEE/CVF International Conference on Computer Vision (ICCV), Montreal, QC, Canada, 2021, pp. 9021–9031, https://doi.org/10.1109/ICCV48922.2021.00891

  40. Afrasiyabi, A., Larochelle, H., Lalonde, J.F., et al.: Matching feature sets for few-shot image classification. In: 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA, pp. 9004–9014 (2022), https://doi.org/10.1109/CVPR52688.2022.00881

  41. Shi, B., Li, W., Huo, J., et al.: Global- and local-aware feature augmentation with semantic orthogonality for few-shot image classification. Pattern Recognit. 142, 109702 (2023)

    Article  Google Scholar 

  42. Hao, F., He, F., Liu, L., et al.: Class-aware patch embedding adaptation for few-shot image classification. In: 2023 International Conference on Computer Vision (ICCV 2023), Paris, France. October 2–3 (2023)

  43. Ma, T., Sun, Y., Yang, Z., et al.: ProD: prompting-to-disentangle domain knowledge for cross-domain few-shot image classification. In: 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada, pp. 19754–19763 (2023)

  44. Dong, J., Wang, Y., Lai, J., et al.: Improving adversarially robust few-shot image classification with generalizable representations. In: 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA, pp. 9015–9024 (2022)

  45. Zhu, Y., Liu, C., Jiang, S., et al.: Multi-attention meta learning for few-shot fine-grained image recognition. In: Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence (IJCAI2020), January 2021 Article No.: 152, pp. 1090–1096

  46. Li, J., Tong, J., Gao, G., et al.: Attention-enhanced relation network for few-shot image classification. In: ICIGP’23: Proceedings of the 2023 6th International Conference on Image and Graphics Processing. pp. 197–203 (2023)

  47. Meng, X., Wang, X., Yin, S., et al.: Few-shot image classification algorithm based on attention mechanism and weight fusion. J. Eng. Appl. Sci. 70, 1–14 (2023)

    Article  Google Scholar 

  48. Fu, W., Zhou, L., Chen, J.: Bidirectional matching prototypical network for few-shot image classification. IEEE Signal Process. Lett. 29, 982–986 (2022). https://doi.org/10.1109/LSP.2022.3152686

    Article  Google Scholar 

  49. Jia, J., Feng, X., Yu, H.: Few-shot classification via efficient meta-learning with hybrid optimization. In: Engineering Applications of Artificial Intelligence, 127(Part A), 107296 (2024)

  50. Shi, M., Ren, J.: A lightweight dense relation network with attention for hyperspectral image few-shot classification. In: Engineering Applications of Artificial Intelligence, 126(Part C), 106993 (2023)

  51. Ren, M., Triantafillou, E., Ravi, S., et al.: Meta-learning for semi-supervised few-shot classification. In: The 6th International Conference on Learning Representations (ICLR 2018), Vancouver, BC, Canada, April 30–May 3 (2018)

  52. Russakovsky, O., Deng, J., Su, H., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. 115, pp. 211–252 (2015)

  53. Lin, Z., Li, M., Zheng, Z., et al.: Self-attention ConvLSTM for spatiotemporal prediction. In: Proceedings of the AAAI Conference on Artificial Intelligence, 34(07), 11531–11538 (2020)

  54. Zhong, Z., Zheng, L., Kang, G., et al.: Random erasing data augmentation. In: Proceedings of the AAAI Conference on Artificial Intelligence. 34(07), 13001–13008 (2020)

Download references

Acknowledgements

This research is supported by the Natural Key R &D Plan Project of China (2022YFE0196100), by the Key R &D program of science and technology foundation of Hebei Province, China (19210310D), by the Natural science foundation of Hebei Province, China (F2021201020), and by the Innovation Capacity Enhancement Program-Science and Technology Platform Project, Hebei Province (22567623H).

Author information

Authors and Affiliations

  1. Hebei Key Laboratory of Machine Learning and Computational Intelligence, College of Mathematics and Information Science, Hebei University, Baoding, 071002, Hebei, China

    Ruizhi Liao, Junhai Zhai & Feng Zhang

Authors
  1. Ruizhi Liao
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Junhai Zhai
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Feng Zhang
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Junhai Zhai.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Liao, R., Zhai, J. & Zhang, F. Optimization model based on attention mechanism for few-shot image classification. Machine Vision and Applications 35, 19 (2024). https://doi.org/10.1007/s00138-023-01502-2

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s00138-023-01502-2

Keywords