Skip to main content
Log in

Multi-local feature relation network for few-shot learning

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

Recently, few-shot learning has received considerable attention from researchers. Compared to deep learning, which requires abundant data for training, few-shot learning only requires a few labeled samples. Therefore, few-shot learning has been extensively used in scenarios in which a large number of samples cannot be obtained. However, effectively extracting features from a limited number of samples are the most important problem in few-shot learning. To solve this limitation, a multi-local feature relation network (MLFRNet) is proposed to improve the accuracy of few-shot image classification. First, we obtain the local sub-images of each image by random cropping, which is used to obtain local features. Second, we propose support-query local feature attention by exploring local feature relationships between the support and query sets. Using the local feature attention, the importance of local features of each class prototype can be calculated to classify query data. Moreover, we explore local feature relationship between the support set and the support set, and we propose support-support local feature similarity. Using local feature similarity, we can adaptively determine the margin loss of the local features, which then improves the network accuracy. Experiments on two benchmark datasets show that the proposed MLFRNet achieves state-of-the-art performance. In particular, for the miniImageNet dataset, the proposed method achieves 66.79% (1-shot) and 83.16% (5-shot) accuracy.

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

Access this article

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

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

Instant access to the full article PDF.

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

Similar content being viewed by others

References

  1. He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770–778

  2. Ji Y, Zhang H, Zhang Z, Liu M (2021) CNN-based encoder–decoder networks for salient object detection: a comprehensive review and recent advances. Inf Sci 546:835–857

    Article  MathSciNet  Google Scholar 

  3. Ronneberger O, Fischer P, Brox T (2015) U-net: convolutional networks for biomedical image segmentation. In: International conference on medical image computing and computer-assisted intervention. Springer, pp 234–241

  4. Schwartz E, Karlinsky L, Shtok J, Harary S, Marder M, Feris R, Kumar A, Giryes R, Bronstein AM (2018) Delta-encoder: an effective sample synthesis method for few-shot object recognition

  5. Gao R, Hou X, Qin J, Chen J, Liu L, Zhu F, Zhang Z, Shao L (2020) Zero-vae-gan: generating unseen features for generalized and transductive zero-shot learning. IEEE Trans Image Process 29:3665–3680. https://doi.org/10.1109/TIP.2020.2964429

    Article  Google Scholar 

  6. Liu L, Zhang H, Xu X, Zhang Z, Yan S (2020) Collocating clothes with generative adversarial networks cosupervised by categories and attributes: a multidiscriminator framework. IEEE Trans Neural Netw Learn Syst 31(9):3540–3554. https://doi.org/10.1109/TNNLS.2019.2944979

    Article  MathSciNet  Google Scholar 

  7. Fe-Fei L et al (2003) A Bayesian approach to unsupervised one-shot learning of object categories. In: Proceedings ninth IEEE international conference on computer vision. IEEE, pp 1134–1141

  8. Finn C, Abbeel P, Levine S (2017) Model-agnostic meta-learning for fast adaptation of deep networks. In: International conference on machine learning. PMLR, pp 1126–1135

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

  10. Gidaris S, Komodakis N (2018) Dynamic few-shot visual learning without forgetting. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4367–4375

  11. Gidaris S, Komodakis N (2019) 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

  12. Lee K, Maji S, Ravichandran A, Soatto S (2019) Meta-learning with differentiable convex optimization. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 10657–10665

  13. Santoro A, Bartunov S, Botvinick M, Wierstra D, Lillicrap T (2016) One-shot learning with memory-augmented neural networks. arXiv:1605.06065

  14. Munkhdalai T, Yu H (2017) Meta networks. In: International conference on machine learning. PMLR, pp 2554–2563

  15. Munkhdalai T, Yuan X, Mehri S, Trischler A (2018) Rapid adaptation with conditionally shifted neurons. In: International conference on machine learning. PMLR, pp 3664–3673

  16. Li H, Eigen D, Dodge S, Zeiler M, Wang X (2019) 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

  17. Vinyals O, Blundell C, Lillicrap T, Kavukcuoglu K, Wierstra D (2016) Matching networks for one shot learning. arXiv:1606.04080

  18. Snell J, Swersky K, Zemel RS (2017) Prototypical networks for few-shot learning. arXiv:1703.05175

  19. Sung F, Yang Y, Zhang L, Xiang T, Torr PH, Hospedales TM (2018) Learning to compare: relation network for few-shot learning. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1199–1208

  20. Oreshkin BN, Rodriguez P, Lacoste A (2018) Tadam: task dependent adaptive metric for improved few-shot learning. arXiv:1805.10123

  21. Hou R, Chang H, Ma B, Shan S, Chen X (2019) Cross attention network for few-shot classification. arXiv:1910.07677

  22. Li A, Huang W, Lan X, Feng J, Li Z, Wang L (2020) Boosting few-shot learning with adaptive margin loss. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 12576–12584

  23. Koch G, Zemel R, Salakhutdinov R (2015) Siamese neural networks for one-shot image recognition. In: ICML deep learning workshop, vol 2. Lille

  24. Satorras VG, Estrach JB (2018) Few-shot learning with graph neural networks. In: International conference on learning representations

  25. Zhong Z, Zheng L, Kang G, Li S, Yang Y (2020) Random erasing data augmentation. In: Proceedings of the AAAI conference on artificial intelligence, vol 34, pp 13001–13008

  26. Ren M, Triantafillou E, Ravi S, Snell J, Swersky K, Tenenbaum J, Larochelle H, Zemel R (2018) Meta-learning for semi-supervised few-shot classification. ICLR

  27. Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, Huang Z, Karpathy A, Khosla A, Bernstein M et al (2015) Imagenet large scale visual recognition challenge. Int J Comput Vis 115(3):211–252

    Article  MathSciNet  Google Scholar 

  28. Kim J, Kim T, Kim S, Yoo CD (2019) Edge-labeling graph neural network for few-shot learning. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 11–20

  29. Chen WY, Liu YC, Kira Z, Wang YCF, Huang JB (2018) A closer look at few-shot classification. In: International conference on learning representations

  30. Chen Y, Wang X, Liu Z, Xu H, Darrell T (2020) A new meta-baseline for few-shot learning. arXiv:2003.04390

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

  32. Raghu A, Raghu M, Bengio S, Vinyals O (2019) Rapid learning or feature reuse? Towards understanding the effectiveness of MAML. CoRR abs/1909.09157 arXiv:1909.09157

Download references

Funding

This work was supported by the National Key R&D Program of China (No. 2018YFC0807500) and by National Natural Science Foundation of China (No. 61806045).

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Guiduo Duan.

Ethics declarations

Conflict of interest

Li Ren declares that he has no conflict of interest. Guiduo Duan has received research grants from the National Key R&D Program of China (No. 2018YFC0807500). Tianxi Huang declares that he has no conflict of interest. Zhao Kang received research grants from National Natural Science Foundation of China (No. 61806045).

Ethical approval

This article does not contain any studies with human participants or animals performed by any of the authors.

Additional information

Publisher's Note

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

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Ren, L., Duan, G., Huang, T. et al. Multi-local feature relation network for few-shot learning. Neural Comput & Applic 34, 7393–7403 (2022). https://doi.org/10.1007/s00521-021-06840-8

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-021-06840-8

Keywords

Navigation