Skip to main content
SpringerLink
Log in

Multi-distance metric network for few-shot learning

  • Original Article
  • Published:
International Journal of Machine Learning and Cybernetics Aims and scope Submit manuscript

Abstract

Few-shot learning aims to make classification when few samples are available. In general, metric-based methods map images into a space by learning the embedding function. However, conventional metric-based methods rely on a single distance value, which does not pay attention to the shallow features. In this paper, we propose a multi-distance metric network (MDM-Net) by employing a multi-output embedding network to map samples into different feature spaces. In addition, we maximize the inter-class distance which is popular in metric learning field to improve the performance of few-shot classifier. Furthermore, we design a task-adaptive margin to adjust the distance between different sample pairs, and we found that the distance loss combined with cross-entropy loss is beneficial to achieve better results in meta-task training. The proposed method is verified by tests on miniImageNet and FC100 these two benchmarks for 5-way 1-shot classification task and 5-way 5-shot classification task with competitive 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
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9

Similar content being viewed by others

References

  1. LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436–444

    Article  Google Scholar 

  2. Krizhevsky A, Sutskever I, Hinton G. (2012) Imagenet classification with deep convolutional neural networks. In: Proceedings of advances in neural information processing systems, pp. 1097–1105

  3. Deng J, Dong W, Socher R, et al. (2009) Imagenet: A large-scale hierarchical image database. In: 2009 IEEE conference on computer vision and pattern recognition, pp. 248–255

  4. Szegedy C, Liu W, Jia Y, et al. (2015) Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 1–9

  5. Liu W, Anguelov D, Erhan D, et al. (2016) SSD: Single shot multibox detector. In: European conference on computer vision, pp. 21–37

  6. Ren S, He K, Girshick R et al (2015) Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell 39(6):1137–1149

    Article  Google Scholar 

  7. Redmon J, Divvala S, Girshick R, et al. (2016) You only look once: Unified, real-time object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 779–788

  8. He K, Gkioxari G, Dollár P, et al. (2017) Mask R-CNN. In: Proceedings of the IEEE international conference on computer vision, pp. 2961–2969

  9. Kong T, Yao A, Chen Y, et al. (2016) Hypernet: towards accurate region proposal generation and joint object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 845–853

  10. Sang J, Guo P, Xiang Z et al (2017) Vehicle detection based on faster-RCNN. J Chongqing Univ 40(7):32–36

    Google Scholar 

  11. Sharif Razavian A, Azizpour H, Sullivan J, et al. (2014) CNN features off-the-shelf: an astounding baseline for recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pp. 806–813

  12. Hawkins DM (2004) The problem of overfitting. J Chem Inf Comput Sci 44(1):1–12

    Article  MathSciNet  Google Scholar 

  13. Srivastava N, Hinton G, Krizhevsky A et al (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15(1):1929–1958

    MathSciNet  MATH  Google Scholar 

  14. Caruana R, Lawrence S, Giles CL. (2001) Overfitting in neural nets: backpropagation, conjugate gradient, and early stopping. In: Advances in neural information processing systems, pp. 402–408

  15. Chawla NV, Bowyer KW, Hall LO et al (2002) SMOTE: synthetic minority over-sampling technique. J Artif Intell Res 16:321–357

    Article  Google Scholar 

  16. Salamon J, Bello JP (2017) Deep convolutional neural networks and data augmentation for environmental sound classification. IEEE Signal Process Lett 24(3):279–283

    Article  Google Scholar 

  17. Cubuk ED, Zoph B, Mane D, et al. (2019) Autoaugment: learning augmentation strategies from data. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 113–123

  18. Socher R, Ganjoo M, Manning CD, et al. (2013) Zero-shot learning through cross-modal transfer. In: Advances in neural information processing systems, pp. 935–943

  19. Ma Y, Cambria E, Gao S (2016) Label embedding for zero-shot fine-grained named entity typing. In: Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pp. 171–180

  20. Jayaraman D, Grauman K (2014) Zero-shot recognition with unreliable attributes. In: Advances in neural information processing systems, pp. 3464–3472

  21. Pan SJ, Yang Q (2009) A survey on transfer learning. IEEE Trans Knowl Data Eng 22(10):1345–1359

    Article  Google Scholar 

  22. Zamir AR, Sax A, Shen W, et al. (2018) Taskonomy: Disentangling task transfer learning. In: Proceedings of the IEEE Conference on computer vision and pattern recognition, pp. 3712–3722

  23. Long M, Zhu H, Wang J, et al. (2016) Unsupervised domain adaptation with residual transfer networks. In: Advances in neural information processing systems, pp. 136–144

  24. Long M, Cao Y, Wang J, et al. (2015) Learning transferable features with deep adaptation networks. In: International conference on machine learning, pp. 97–105

  25. Tzeng E, Hoffman J, Saenko K, et al. (2017) Adversarial discriminative domain adaptation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 7167–7176

  26. Lake BM, Salakhutdinov RR, Tenenbaum J (2013) One-shot learning by inverting a compositional causal process. In: Advances in neural information processing systems, pp. 2526–2534

  27. Xie R, Liu Z, Jia J, et al. (2016) Representation learning of knowledge graphs with entity descriptions. In: Thirtieth AAAI conference on artificial intelligence, pp. 2659–2665

  28. Triantafillou E, Zemel R, Urtasun R. (2017) Few-shot learning through an information retrieval lens. In: Proceedings of the 31st international conference on neural information processing systems, pp. 2252–2262

  29. Santoro A, Bartunov S, Botvinick M, et al. (2016) Meta-learning with memory-augmented neural networks. In: International conference on machine learning, pp. 1842–1850

  30. Ravi S, Larochelle H. (2017) Optimization as a model for few-shot learning. In: Proceedings of the 5th international conference on learning representations. Toulon, France: ICLR, pp. 4077–4087

  31. Oreshkin B, López PR, Lacoste A. (2018) Tadam: Task dependent adaptive metric for improved few-shot learning. In: Advances in neural information processing systems, pp. 721–731

  32. Cheng G, Zhou P, Han J (2017) Duplex metric learning for image set classification. IEEE Trans Image Process 27(1):281–292

    Article  MathSciNet  Google Scholar 

  33. Zhang H, Berg AC, Maire M, et al. (2006) SVM-KNN: Discriminative nearest neighbor classification for visual category recognition. In: 2006 IEEE computer society conference on computer vision and pattern recognition, pp. 2126–2136

  34. Liu X, Zhou F, Liu J et al (2020) Meta-Learning based prototype-relation network for few-shot classification. Neurocomputing 383:224–234

    Article  Google Scholar 

  35. Vinyals O, Blundell C, Lillicrap T, et al. (2016) Matching networks for one shot learning. In: Proceedings of advances in neural information processing systems, pp. 3630–3638

  36. Schroff F, Kalenichenko D, Philbin J (2015) FaceNet: a unified embedding for face recognition and clustering. In: Computer vision and pattern recognition, pp. 815–823

  37. Oreshkin BN, Lopez PR, Lacoste A. (2018) TADAM: task dependent adaptive metric for improved few-shot learning. In: Neural information processing systems, pp. 721–731

  38. Koch G, Zemel R, Salakhutdinov R (2015) Siamese neural networks for one-shot image recognition. In: ICML deep learning workshop, pp. 1–2

  39. Snell J, Swersky K, Zemel R (2017) Prototypical networks for few-shot learning. In: Proceedings of advances in neural information processing systems. pp. 4077–4087

  40. Li W, Wang L, Xu J, et al. (2019) Revisiting local descriptor based image-to-class measure for few-shot learning. In: Computer vision and pattern recognition, pp. 7260–7268

  41. Li W, Wang L, Huo J, et al. (2020) Asymmetric distribution measure for few-shot learning. In: Proceedings of the twenty-ninth international joint conference on artificial intelligence, pp. 2957–2963

  42. Chen H, Li H, Li Y, et al. (2021) Multi-level Metric Learning for Few-shot Image Recognition. arXiv:2103.11383; https://arxiv.org/abs/2103.11383v11383

  43. Wang Y, Chao W, Weinberger KQ, et al. (2019) SimpleShot: Revisiting nearest-neighbor classification for few-shot learning. arXiv:1911.04623. https://arxiv.org/abs/1911.04623

  44. Berthelot D, Carlini N, Goodfellow I, et al. (2019) MixMatch: a holistic approach to semi-supervised learning. In: neural information processing systems, pp. 5049–5059

  45. Krizhevsky A, Nair V, Hinton G (2009) Cifar-10 and cifar-100 datasets. URl: https://www.cs.toronto.edu/kriz/cifar.html:

  46. Munkhdalai T, Yu H (2017) Meta networks. In: Proceedings of the 34th international conference on machine learning, pp. 2554–2563

  47. Finn C, Abbeel P, Levine S. (2017) Model-agnostic meta-learning for fast adaptation of deep networks. In: Proceedings of the 34th international conference on machine learning, pp. 1126–1135

  48. Finn C, Xu K, Levine S. (2018) Probabilistic model-agnostic meta-learning. In: Neural information processing systems, pp. 9516–9527

  49. Satorras VG, Estrach JB (2018) Few-shot learning with graph neural networks. In: 6th international conference on learning representations, pp. 1–13

  50. Sung F, Yang Y, Zhang L, et al. (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

  51. Lee Y, Choi S. (2018) Gradient-based meta-learning with learned layerwise metric and subspace. In: International conference on machine learning, pp. 2927–2936

  52. Mishra N, Rohaninejad M, Chen X, et al. (2018) A simple neural attentive meta-learner. In: 6th international conference on learning representations, pp. 1–17

  53. Munkhdalai T, Yuan X, Mehri S, et al. (2018) Rapid adaptation with conditionally shifted neurons. In: International conference on machine learning, pp. 3661–3670

  54. Liu Y, Lee J, Park M, et al. (2019) Learning to propagate labels: Transductive propagation network for few-shot learning. In: 7th international conference on learning representations, pp. 1–11

  55. Sun Q, Liu Y, Chua T, et al. (2019) Meta-transfer learning for few-shot learning. In: Computer vision and pattern recognition, pp. 403–412

  56. Chen W, Liu Y, Kira Z, et al. (2019) A closer look at few-shot classification. In: 7th international conference on learning representations., pp. 1–17

  57. Lee K, Maji S, Ravichandran A, et al. (2019) Meta-learning with differentiable convex optimization. In: Computer vision and pattern recognition, pp. 10657–10665

  58. Lifchitz Y, Avrithis Y, Picard S, et al. (2019) Dense classification and implanting for few-shot learning. In: Computer vision and pattern recognition, pp. 9258–9267

Download references

Acknowledgements

This work was supported by the National Key Research and Development Program of China (2018AAA0101601), and the Zhejiang Provincial Natural Science Foundation of China (LY20E050011).

Author information

Authors and Affiliations

  1. School of Automation, Hangzhou Dianzi University, Hangzhou, 310018, China

    Farong Gao, Lijie Cai & Zhangyi Yang

  2. Department of Automation, Tsinghua University, Beijing, 100084, China

    Shiji Song & Cheng Wu

Authors
  1. Farong Gao
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Lijie Cai
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Zhangyi Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Shiji Song
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Cheng Wu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Farong Gao.

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

Gao, F., Cai, L., Yang, Z. et al. Multi-distance metric network for few-shot learning. Int. J. Mach. Learn. & Cyber. 13, 2495–2506 (2022). https://doi.org/10.1007/s13042-022-01539-1

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s13042-022-01539-1

Keywords

Search

Navigation