Skip to main content
SpringerLink
Log in

Discriminant space metric network for few-shot image classification

  • Published:
Applied Intelligence Aims and scope Submit manuscript

Abstract

Metric-based few-shot learning has gained considerable attention for simply and effectively addressing the few-shot classification problem. However, a huge number of the existing approaches focus only on the similarity or distance between features of the instances in the embedding space, neglecting the geometric structure of the samples. To remedy this, we propose a novel approach referred to as the discriminant space metric network (DSMNet) for few-shot image classification problem. DSMNet exploits the geometric structure of the samples within each episode to enhance the discriminative ability of the embedding space. Specifically, DSMNet aims to increase the distance between features belonging to different classes while making those from the same class more compact by maximizing the between-class scatter and minimizing the within-class scatter in the embedding space. Moreover, we developed a novel adaptation strategy for improving the model’s generalizing capability. Extensive experiments are conducted on four few-shot classification benchmark datasets to demonstrate the proposed DSMNet. We also performed several ablation studies to analyze its performance. The superiority of DSMNet over existing networks is indicated by the experimental results.

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

Access this article

Log in via an institution

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
Algorithm 1
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9

Similar content being viewed by others

Availability of data and materials

The datasets used during this study are available upon reasonable request to the authors.

Code Availability

Code availability: The code is publicly available at https://github.com/ylshitou/DSMNet.

References

  1. Zhou H, Zhang S, Peng J, Zhang S, Li J, Xiong H, Zhang W (2021) Informer: Beyond efficient transformer for long sequence time-series forecasting. In: Proceedings of association for the advance of artificial intelligence

  2. Chen Y, Chiang S-W, Wu M (2022) A few-shot transfer learning approach using text-label embedding with legal attributes for law article prediction. Appl Intell 52(3):2884–2902

    Article  Google Scholar 

  3. Chen L, Min Y, Zhang M, Karbasi A (2020) More data can expand the generalization gap between adversarially robust and standard models. In: Proceedings of the international conference on machine learning, pp 1670–1680

  4. Dvornik N, Schmid C, Mairal J (2019) Diversity with cooperation: Ensemble methods for few-shot classification. In: Proceedings of the IEEE international conference on computer vision, pp 3723–3731

  5. Bronskill J, Gordon J, Requeima J, Nowozin S, Turner R (2020) Tasknorm: Rethinking batch normalization for meta-learning. In: Proceedings of the international conference on machine learning, pp 1153–1164

  6. Yan L, Zhang L, Zheng X, Li F (2021) Deeper multi-column dilated convolutional network for congested crowd understanding. Neural Comput Appl:1–16

  7. 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 

  8. Lin T, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Dollár P, Zitnick CL (2014) Microsoft COCO: Common objects in context. In: Proceedings of the European conference on computer vision, pp 740–755

  9. Li X, Chang D, Ma Z, Tan Z, Xue J, Cao J, Yu J, Guo J (2020) OSLNet: Deep small-sample classification with an orthogonal softmax layer. IEEE Trans Image Process 29:6482–6495

    Article  MathSciNet  MATH  Google Scholar 

  10. Li X, Sun Z, Xue J, Ma Z (2021) A concise review of recent few-shot meta-learning methods. Neurocomputing 456:463–468

    Article  Google Scholar 

  11. Yao H, Wu X, Tao Z, Li Y, Ding B, Li R, Li Z (2020) Automated relational meta-learning. In: Proceedings of the international conference on learning representations

  12. Jiang M, Li F, Liu L (2022) Continual meta-learning algorithm. Appl Intell 52(4):4527–4542

    Article  Google Scholar 

  13. Yin M, Tucker G, Zhou M, Levine S, Finn C (2020) Meta-learning without memorization. In: Proceedings of the international conference on learning representations

  14. Jiang M, Li F (2022) Lie group continual meta learning algorithm. Appl Intell 52(10):10965–10978

    Article  Google Scholar 

  15. Li L, Jin W, Huang Y (2022) Few-shot contrastive learning for image classification and its application to insulator identification. Appl Intell 52(6):6148–6163

    Article  Google Scholar 

  16. Rakelly K, Shelhamer E, Darrell T, Efros AA, Levine S (2019) Few-shot segmentation propagation with guided networks. In: Proceedings of the international conference on machine learning

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

  18. Ravi S, Larochelle H (2017) Optimization as a model for few-shot learning. In: Proceedings of the international conference on learning representations

  19. Li W, Wang L, Xu J, Huo J, Gao Y, Luo J (2019) Revisiting local descriptor based image-to-class measure for few-shot learning. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7260–7268

  20. Chen Z, Fu Y, Zhang Y, Jiang Y-G, Xue X, Sigal L (2019) Multi-level semantic feature augmentation for one-shot learning. IEEE Trans Image Process 28(9):4594–4605

    Article  MathSciNet  MATH  Google Scholar 

  21. Antoniou A, Edwards H, Storkey A (2018) How to train your MAML. In: Proceedings of the international conference on learning representations

  22. Bi S, Wang Y, Li X, Dong M, Zhu J (2022) Critical direction projection networks for few-shot learning. Appl Intell 52(5):5400–5413

    Article  Google Scholar 

  23. Snell J, Swersky K, Zemel RS (2017) Prototypical networks for few-shot learning. In: Advances in neural information processing systems, pp 4077–4087

  24. Chen W, Liu Y, Kira Z, Wang YF, Huang J (2019) A closer look at few-shot classification. In: Proceedings of the international conference on learning representations

  25. Tseng H, Lee H, Huang J, Yang M (2020) Cross-domain few-shot classification via learned feature-wise transformation. In: Proceedings of the international conference on learning representations

  26. 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

  27. Garcia V, Bruna J (2018) Few-shot learning with graph neural networks. In: Proceedings of the international conference on learning representations

  28. Huang H, Wu Z, Li W, Huo J, Gao Y (2021) Local descriptor-based multi-prototype network for few-shot learning. Pattern Recogn 116:107935

    Article  Google Scholar 

  29. Liu X, Zhou F, Liu J, Jiang L (2020) Meta-learning based prototype-relation network for few-shot classification. Neurocomputing 383:224–234

    Article  Google Scholar 

  30. Yan L, Zhang L (2019) Unsupervised dimension reduction using supervised orthogonal discriminant projection for clustering. In: International conference on high performance computing and communications, pp 2239–2246

  31. Shu X, Gao Y, Lu H (2012) Efficient linear discriminant analysis with locality preserving for face recognition. Pattern Recogn 45(5):1892–1898

    Article  MATH  Google Scholar 

  32. Rusu AA, Rao D, Sygnowski J, Vinyals O, Pascanu R, Osindero S, Hadsell R (2019) Meta-learning with latent embedding optimization. In: Proceedings of the international conference on learning representations

  33. Vinyals O, Blundell C, Lillicrap T, kavukcuoglu k, Wierstra D (2016) Matching networks for one shot learning. In: Advances in neural information processing systems, vol 29, pp 3630–3638

  34. Xu R, Xing L, Shao S, Zhao L, Liu B, Liu W, Zhou Y (2022) GCT: Graph co-training for semi-supervised few-shot learning. IEEE Trans Circuits Syst Video Technol:1–1

  35. Shao S, Xing L, Wang Y, Xu R, Zhao C, Wang Y, Liu B (2021) MHFC: Multi-head feature collaboration for few-shot learning. In: Proceedings of the 29th ACM international conference on multimedia, pp 4193–4201

  36. Shao S, Xing L, Xu R, Liu W, Wang Y, Liu B (2022) MDFM: Multi-decision fusing model for few-shot learning. IEEE Trans Circ Syst Video Technol 32(8):5151–5162

    Article  Google Scholar 

  37. Wang Y, Xu C, Liu C, Zhang L, Fu Y (2020) Instance credibility inference for few-shot learning. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 12836–12845

  38. Finn C, Xu K, Levine S (2018) Probabilistic model-agnostic meta-learning. Adv Neural Inf Process Syst:31

  39. Munkhdalai T, Yu H (2017) Meta networks. In: Proceedings of the international conference on machine learning, pp 2554–2563

  40. Zhang R, Che T, Ghahramani Z, Bengio Y, Song Y (2018) MetaGAN: An adversarial approach to few-shot learning. Adv Neural Inf Process Syst:31

  41. Hariharan B, Girshick R (2017) Low-shot visual recognition by shrinking and hallucinating features. In: Proceedings of the IEEE international conference on computer vision, pp 3018–3027

  42. Gao H, Shou Z, Zareian A, Zhang H, Chang S (2018) Low-shot learning via covariance-preserving adversarial augmentation networks. Adv Neural Inf Process Syst:31

  43. Wang Y-X, Girshick R, Hebert M, Hariharan B (2018) Low-shot learning from imaginary data. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7278–7286

  44. Antoniou A, Storkey A, Edwards H (2017) Data augmentation generative adversarial networks. arXiv:1711.04340

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

  46. Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. In: Proceedings of the international conference on learning representations

  47. Oreshkin BN, López PR, Lacoste A (2018) TADAM: Task dependent adaptive metric for improved few-shot learning. In: Advances in neural information processing systems

  48. Qiao S, Liu C, Shen W, Yuille AL (2018) Few-shot image recognition by predicting parameters from activations. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7229–7238

  49. Allen K, Shelhamer E, Shin H, Tenenbaum J (2019) Infinite mixture prototypes for few-shot learning. In: Proceedings of the international conference on machine learning, pp 232–241

  50. Triantafillou E, Zhu T, Dumoulin V, Lamblin P, Evci U, Xu K, Goroshin R, Gelada C, Swersky K, Manzagol P-A et al (2019) Meta-dataset: A dataset of datasets for learning to learn from few examples. In: Proceedings of the international conference on learning representations

  51. Wah C, Branson S, Welinder P, Perona P, Belongie S (2011) The Caltech-UCSD Birds-200-2011 dataset

  52. Khosla A, Jayadevaprakash N, Yao B, Li F-F (2011) Novel dataset for fine-grained image categorization: Stanford dogs. In: Proceedings of the CVPR workshop on fine-grained visual categorization (FGVC), vol 2

  53. Bertinetto L, Henriques JF, Torr PHS, Vedaldi A (2019) Meta-learning with differentiable closed-form solvers. In: Proceedings of the international conference on learning representations

  54. Hilliard N, Phillips L, Howland S, Yankov A, Corley CD, Hodas NO (2018) Few-shot learning with metric-agnostic conditional embeddings. arXiv:1802.04376

  55. Krizhevsky A, Hinton G et al (2009) Learning multiple layers of features from tiny images. University of Toronto, ON, Canada

  56. Bertinetto L, Henriques JF, Valmadre J, Torr P, Vedaldi A (2016) Learning feed-forward one-shot learners. Adv Neural Inf Process Syst:29

  57. Kingma DP, Ba J (2015) Adam: A method for stochastic optimization. In: Proceedings of the international conference on learning representations

  58. Li W, Xu J, Huo J, Wang L, Gao Y, Luo J (2019) Distribution consistency based covariance metric networks for few-shot learning. In: Proceedings of the AAAI conference on artificial intelligence, vol 33, pp 8642–8649

  59. Raghu A, Raghu M, Bengio S, Vinyals O (2020) Rapid learning or feature reuse? towards understanding the effectiveness of MAML. In: Proceedings of the international conference on learning representations

  60. Qin Y, Zhang W, Zhao C, Wang Z, Zhu X, Shi J, Qi G, Lei Z (2021) Prior-knowledge and attention based meta-learning for few-shot learning. Knowl-Based Syst 213:106609

    Article  Google Scholar 

  61. Li X, Wu J, Sun Z, Ma Z, Cao J, Xue J-H (2021) Bsnet: Bi-similarity network for few-shot fine-grained image classification. IEEE Trans Image Process 30:1318–1331

    Article  MathSciNet  Google Scholar 

  62. Xue Z, Xie Z, Xing Z, Duan L (2020) Relative position and map networks in few-shot learning for image classification. In: IEEE conference on computer vision and pattern recognition workshops, pp 4032–4036

  63. Selvaraju RR, Cogswell M, Das A, Vedantam R, Parikh D, Batra D (2017) Grad-CAM: Visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE international conference on computer vision, pp 618–626

  64. Van der Maaten L, Hinton G (2008) Visualizing data using t-SNE. J Mach Learn Res 9(11)

  65. 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

  66. Sergey Z, Nikos K (2016) Wide residual networks. In: Proceedings of the British machine vision conference, pp 1–12

Download references

Acknowledgements

We would like to thank Chengxiang Hu, Meijuan Su and Mengjuan Jiang for their technical support. We would also like to thank the computer resources and other support provided by the Machine Learning Laboratory of Soochow University.

Funding

This work was supported in part by the Priority Academic Program Development of Jiangsu Higher Education Institutions, by the National Key R&D Program of China (2018YFA0701700; 2018YFA0701701) and by the National Natural Science Foundation of China under Grant No.61672364, No.62176172 and No.61902269.

Author information

Authors and Affiliations

  1. School of Computer Science and Technology Joint International Research Laboratory of Machine Learning and Neuromorphic Computing, Soochow University, No.1 ShiZi Street, Su Zhou, 215006, Jiang Su, China

    Leilei Yan, Li Zhang & Xiaohan Zheng

  2. School of Computer Science and Technology, Soochow University, 215006, Suzhou, China

    Fanzhang Li

Authors
  1. Leilei Yan
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Fanzhang Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Li Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Xiaohan Zheng
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

All authors contributed to the study conception and design. Leilei Yan: Conceptualization, Methodology, Software, Validation, Writing - original draft, Writing - review and editing. Fanzhang Li: Conceptualization, Methodology, Software, Writing - review and editing, Validation, Project administration, Funding acquisition. Li Zhang: Investigation, Software, Visualization, Writing - review and editing. Xiaohan Zheng: Investigation, Software, Visualization. All authors commented on previous versions of the manuscript. All authors read and approved the final manuscript.

Corresponding author

Correspondence to Fanzhang Li.

Ethics declarations

Ethics approval

Not applicable.

Consent for Publication

Not applicable.

Consent to participate

Not applicable.

Competing interests

The authors declare that they have no competing interests.

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

Yan, L., Li, F., Zhang, L. et al. Discriminant space metric network for few-shot image classification. Appl Intell 53, 17444–17459 (2023). https://doi.org/10.1007/s10489-022-04413-3

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10489-022-04413-3

Keywords

Search

Navigation