Skip to main content
SpringerLink
Log in

Enhancement of Few-shot Image Classification Using Eigenimages

  • Regular Papers
  • Intelligent Control and Applications
  • Published:
International Journal of Control, Automation and Systems Aims and scope Submit manuscript

Abstract

In this paper, we propose an auxiliary loss function called an eigen loss to reduce the overfitting of few-shot learning algorithms. The proposed loss function predicts the class of unlabeled query images by measuring the similarity between the query image and reconstructed image constructed from the eigenimages of the support data. The eigen loss is used in a linearly combined form with the existing loss function of few-shot learning models. Experimental results of the eigen loss applied to representative few-shot learning models on widely used datasets (i.e., MiniImageNet, CUB, and TieredImageNet) show that the proposed method yields notable improvements in terms of classification accuracy.

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

Similar content being viewed by others

References

  1. S. Pankov, “Configuration path control,” International Journal of Control, Automation, and Systems, vol. 21, pp. 306–317, 2023.

    Article  Google Scholar 

  2. W. Li, M. Yue, J. Shanguan, and Y. Jun, “Navigation of mobile robots based on deep reinforcement learning: Reward function optimization and knowledge transfer,” International Journal of Control, Automation, and Systems, vol. 21, pp. 563–574, 2023.

    Article  Google Scholar 

  3. A. Krizhevsky, I. Sutskever, and G. E. Hinton, “ImageNet classification with deep convolutional neural networks,” Advances in Neural Information Processing Systems, vol. 60, no. 6, pp. 84–90, 2017.

    Google Scholar 

  4. K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” arXiv preprint, arXiv:1409.1556, 2014.

  5. O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. Bernstein, A. C. Berg, and F.-F. Li, “Imagenet large scale visual recognition challenge,” International Journal of Computer Vision, vol. 115, pp. 211–252, 2015.

    Article  MathSciNet  Google Scholar 

  6. K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778, 2016.

  7. C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich, “Going deeper with convolutions,” Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–9, 2015.

  8. M. Sornam, K. Muthusubash, and V. Vanitha, “A survey on image classification and activity recognition using deep convolutional neural network architecture,” Proc. of 9th International Conference on Advanced Computing (ICoAC), pp. 121–126, IEEE, 2017.

  9. A. R. Feyjie, R. Azad, M. Pedersoli, C. Kauffman, I. B. Ayed, and J. Dolz, “Semi-supervised few-shot learning for medical image segmentation,” arXiv preprint, arXiv:2003.08462, 2020.

  10. Y. Wang and Q. Yao, “Few-shot learning: A survey,” Proc.of CoRR, 2019.

  11. W. Wang, V. W. Zheng, H. Yu, and C. Miao, “A survey of zero-shot learning: Settings, methods, and applications,” ACM Transactions on Intelligent Systems and Technology (TIST), vol. 10, no. 2, pp. 1–37, 2019.

    Google Scholar 

  12. A. Bellet, A. Habrard, and M. Sebban, “A survey on metric learning for feature vectors and structured data,” arXiv preprint, arXiv:1306.6709.

  13. J. Snell, K. Swersky, and R. S. Zemel, “Prototypical networks for few-shot learning,” Advances in Neural Information Processing Systems, vol. 30, 2017.

  14. O. Vinyals, C. Blundell, T. Lillicrap, K. Kavukcuoglu, and D. Wierstra, “Matching networks for one shot learning,” Advances in Neural Information Processing Systems, vol. 29, 2016.

  15. F. Sung, Y. Yang, L. Zhang, T. Xiang, P. H. S. Torr, and T. M. Hospedales, “Learning to compare: Relation network for few-shot learning,” Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1199–1208, 2018.

  16. H. Tseng, H. Lee, J. Huang, et al., International Conference on Learning Representations (ICLR), 2020.

  17. C. Finn, P. Abbeel, and S. Levine, “Model-agnostic meta-learning for fast adaptation of deep networks,” Proc. of International Conference on Machine Learning, pp. 1126–1135, PMLR, 2017.

  18. S. Ravi and H. Larochelle, “Optimization as a model for few-shot learning,” Proc. of International Conference on Learning Representations (ICLR), 2017.

  19. N. Mishra, M. Rohaninejad, X. Chen, and P. Abbeel, “Meta-learning with temporal convolutions,” arXiv preprint, arXiv:1707.03141, 2017.

  20. A. Nichol, J. Achiam, and J. Schulman, “On firstorder meta-learning algorithms,” arXiv preprint, arXiv:1803.02999, 2018.

  21. Q. Sun, Y. Liu, T.-S. Chua, and B. Schiele, “Meta-transfer learning for few-shot learning,” Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 403–412, 2019.

  22. N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov, “Dropout: A simple way to prevent neural networks from overfitting,” The Journal of Machine Learning Research, vol. 15. no. 56, pp. 1929–1958, 2014.

    MathSciNet  MATH  Google Scholar 

  23. H.-Y. Tseng, Y.-W. Chen, Y.-H. Tsai, S. Liu, Y.-Y. Lin and M.-H. Yang, “Regularizing meta-learning via gradient dropout,” Proc. of the Asian Conference on Computer Vision, 2020.

  24. D. Chen, Y. Chen, Y. Li, R>Mao, Y. He, and H. Xie, “Self-supervised learning for few-shot image classification,” Proc. of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1745–1749, IEEE, 2021.

  25. R. Hou, H. Chang, B. MA, S. Shan, X. Chen, “Cross attention network for few-shot classification,” Advances in Neural Information Processing Systems, vol. 32, 2019.

  26. J. Rajendran, A. Irpan, and E. Jang, “Meta-learning requires meta-augmentation,” Advances in Neural Information Processing Systems, vol. 33, 5705–5715, 2020.

    Google Scholar 

  27. Y. Wang, C. Xu, C. Liu, L. Zhang, and Y. Fi, “Instance credibility inference for few-shot learning,” Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 12836–12845, 2020.

  28. M. Boudiaf, I. Ziko, J. Rony, J. Dolz, P. Piantanida, and I. B. Ayed, “Information maximization for few-shot learning,” Advances in Neural Information Processing Systems, vol. 33, pp. 2445–2457, 2020.

    Google Scholar 

  29. Y. Liu, J. Lee, M. Park, S. Kim, E>Yang, S. J. Hwang, and Y. Yang, “Learning to propagate labels: Transductive propagation network for few-shot learning,” arXiv preprint, arXiv:1805.10002, 2018.

  30. C. Wah, S. Branson, P. Welinder, et al., “The caltech-ucsd birds-200-2011 dataset,” 2011.

  31. G. Koch, R. Zemel, and R. Salakhutdinov, “Siamese neural networks for one-shot image recognition,” Proc. of the 32 nd International Conference on Machine Learning, Lille, France, 2015.

  32. L. Sirovich and M. Kirby, “Low-dimensional procedure for the characterization of human faces,” Journal of the Optical Society of America A, vol. 4, no. 3, pp. 519–524, 1987.

    Article  Google Scholar 

  33. M. Turk and A. P. Pentland, “Face recognition using eigenfaces,” Proc. of 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 586–587, 1991.

  34. A. Santoro, S. Bartunov, M. Botvinick, D. Wierstra, and T. Lillicrap, “Meta-learning with memory-augmented neural networks,” Proc. of the 33rd International Conference on International Conference on Machine Learning, vol. 48, pp. 1842–1850, 2016.

    Google Scholar 

  35. S. Gidaris and N. Komodakis, “Generating classification weights with gnn denoising autoencoders for few-shot learning,” Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 21–30, 2019.

  36. N. Mishra, M. Rohaninejad, X. Chen, and P. Abbeel, “A simple neural attentive meta-learner,” arXiv preprint, arXiv:1707.03141, 2018.

  37. K. Lee, S. Maji, A. Ravichandran, and S. Soatto, “Meta-learning with differentiable convex optimization,” Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10657–10665, 2019.

  38. M. Turk and A. Pentland, “Eigenfaces for recognition,” Journal of Cognitive Neuroscience, vol. 3, no. 1, pp. 71–86, 2991.

  39. M. Ren, E. Triantafillou, S. Ravi, J. Snell, K. Swersky, J. B. Tenenbaum, H. Larochelle, and R. S. Zemel, “Meta-learning for semi-supervised few-shot classification,” arXiv preprint, arXiv:1803.00676, 2018.

  40. W.-Y. Chen, Y.-C. Liu, Z. Kira, Y.-C. F. Wang, and J.-B. Huang, “A closer look at few-shot classification,” Proc. of International Conference on Learning Representations (ICLR), 2019.

  41. D. P. Kingma and J. Ba, “Adam: A method for stochastic optimization,” arXiv preprint, arXiv:1412.6980, 2014.

  42. P. Bachman, R. D. Hjelm, and W. Buchwalter, “Learning representations by maximizing mutual information across views,” Advances in Neural Information Processing Systems, vol. 32, 2019.

Download references

Author information

Authors and Affiliations

  1. Department of Artificial Intelligence, Korea University, Seoul, 02841, Korea

    Jonghyun Ko & Wonzoo Chung

Authors
  1. Jonghyun Ko
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Wonzoo Chung
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Wonzoo Chung.

Ethics declarations

The authors declare there are no conflicts of interest found to influence the work of the paper.

Additional information

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

This work was supported by Institute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government (MSIT) (No. 2019-0-00079, Artificial Intelligence Graduate School Program(Korea University)), and Institute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government (MSIT) (No. 2021-0-02068, Artificial Intelligence Innovation Hub).

Jonghyun Ko received his bachelor’s degree from Dongguk University, Seoul, Korea, in 2020. He is currently pursuing a master’s degreee in Korea University, Seoul, Korea. His current research interests include few-shot learning, machine learning, and deep learning.

Wonzoo Chung received his Ph.D. degree from Cornell University, Ithaca, NY, USA, in 2003. He is currently a Professor with Korea University, Seoul, Korea. His current research interests include statistical machine learning and deep learning.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Ko, J., Chung, W. Enhancement of Few-shot Image Classification Using Eigenimages. Int. J. Control Autom. Syst. 21, 4088–4097 (2023). https://doi.org/10.1007/s12555-023-0105-4

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12555-023-0105-4

Keywords

Search

Navigation