Skip to main content
SpringerLink
Log in

Multi-scale feature network for few-shot learning

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

Few-shot learning aims to learn a classifier that has good generalization performance in new classes, where each class only a small number of labeled examples are available. The existing few-shot classification methods use the single-scale image do not learn effective feature representation. Moreover, most of previous methods still depend on standard metrics to calculate visual similarities, such as Euclidean or cosine distance. Standard metrics are independent of data and lack nonlinear internal structure that captures the similarity between data. In this paper, we propose a new method for few-shot learning problem, which learns a multi-scale feature space, and classification is performed by computing similarities between the multi-scale representation of the image and the label feature of each class (i.e. class representation). Our method, called the Multi-Scale Feature Network (MSFN), is trained end-to-end from scratch. The proposed method improves 1-shot accuracy from 50.44% to 54.48% and 5-shot accuracy from 68.2% to 69.06% on MiniImagenet dataset compared to competing approaches. Experimental results on Omniglot, MiniImagenet, Cifar100, CUB200, and Caltech256 datasets demonstrate the effectiveness of the proposed method.

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

Similar content being viewed by others

References

  1. Boney R, Ilin A (2017) Semi-supervised few-shot learning with prototypical networks. arXiv preprint arXiv:1711.10856

  2. Chen Z, Fu Y, Zhang Y, Jiang YG, Xue X, Sigal L (2018) Semantic feature augmentation in few-shot learning. arXiv preprint arXiv:1804.05298

  3. Dixit M, Kwitt R, Niethammer M, Vasconcelos N (2017) Aga: Attribute-guided augmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 7455-7463

  4. Edwards H, Storkey A (2017) Towards a neural Statistician. arXiv preprint arXiv:1606.02185

  5. Feifei L, Fergus R, Perona P (2006) One-shot learning of object categories. IEEE Transact Pattern Analysis Mach Intell (TPAMI) 28(4):594–611

    Article  Google Scholar 

  6. 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-Volume 70, pp 1126-1135. JMLR.org

  7. Ge W, Yu Y (2017). Borrowing treasures from the wealthy: Deep transfer learning through selective joint fine-tuning. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1086-1095

  8. Girshick R (2015) Fast R-CNN. In Proceedings of the IEEE international conference on computer vision, pp 1440–1448

  9. 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.

  10. 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.

  11. Hilliard N, Hodas NO, Corley CD (2017) Dynamic input structure and network assembly for few-shot learning. arXiv preprint arXiv:1708.06819

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

  13. Huang G, Liu Z, Van der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks.  In Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2261-2269

  14. Kaiser L, Nachum O, Roy A, Bengio S (2017) Learning to remember rare events. In International Conference on Learning Representations (ICLR)

  15. Kingma DP, Ba J (2015)  Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980

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

  17. Krizhevsky A, Sutskever I, Hinton GE (2012) ImageNet classification with deep convolutional neural networks. In Advances in neural information processing systems, pp 1097-1105

  18. Li Z, Zhou F, Chen F, Li H (2017) Meta-SGD: Learning to learn quickly for few-shot learning. arXiv preprint arXiv:1707.09835

  19. Mehrotra A, Dukkipati A (2017) Generative adversarial residual pairwise networks for one shot learning. arXiv preprint arXiv:1703.08033

  20. Mishra N, Rohaninejad M, Chen X, Abbeel P (2018) A simple neural attentive meta-learner. arXiv preprint arXiv:1707.03141

  21. Munkhdalai T, Yu H (2017) Meta networks. In Proceedings of the 34th International Conference on Machine Learning-Volume 70, pp 2554-2563. JMLR. org

  22. Ravi S, Larochelle H (2017) Optimization as a model for few-shot learning. In: International Conference on Learning Representations (ICLR)

  23. Ren S, He K, Girshick R, Sun J (2015) Faster r-cnn: Towards real-time object detection with region proposal networks. In Advances in neural information processing systems, pp 91-99

  24. Ren M, Triantafillou E, Ravi S, Snell J, Swersky K, Tenenbaum J, Larochelle H, Zemel RS (2018) Meta-learning for semi-supervised few-shot classification. arXiv preprint arXiv:1803.00676

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

  26. Garcia V, Bruna J (2017) Few-shot learning with graph neural networks. arXiv preprint arXiv:1711.04043.

  27. Snell J, Swersky K, Zemel R (2017) Prototypical networks for few-shot learning. In Advances in Neural Information Processing Systems, pp 4077-4087

  28. 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

  29. Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich, A (2015) Going deeper with convolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1–9

  30. Thrun S (1996) Learning to learn: introduction. Kluwer Academic Publishers, Dordrecht

    MATH  Google Scholar 

  31. Vinyals O, Blundell C, Lillicrap T, Kavukcuoglu K, Wierstra D (2016)  Matching networks for one shot learning. In Advances in neural information processing systems, pp 3630-3638

  32. Wang P, Liu L, Shen C, Huang Z, van den Hengel A, Tao Shen H (2017) Multi-attention network for one shot learning. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 2721-2729

  33. Wang Y, 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

  34. Ye M, Guo Y (2018) Deep triplet ranking networks for one-shot recognition. arXiv preprint arXiv:1804.07275

  35. Zhou F, Wu B, Li Z (2018) Deep Meta-learning: learning to learn in the concept space. arXiv preprint arXiv:1802.03596.

Download references

Funding

This study was funded by the National Natural Science Foundation of China under (grant number 61672202).

Author information

Authors and Affiliations

  1. School of Computer and Information, Hefei University of Technology, Hefei, 230009, China

    Mengya Han, Ronggui Wang, Juan Yang, Lixia Xue & Min Hu

Authors
  1. Mengya Han
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Ronggui Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Juan Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Lixia Xue
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Min Hu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Juan Yang.

Ethics declarations

Conflict of interest

The whole authors are fulltime teachers of Hefei University of Technology besides the first author Mengya Han, and she is the fulltime student of Hefei University of Technology. The whole authors declare that we have no conflicts of interest to this work.

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

Han, M., Wang, R., Yang, J. et al. Multi-scale feature network for few-shot learning. Multimed Tools Appl 79, 11617–11637 (2020). https://doi.org/10.1007/s11042-019-08413-3

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-019-08413-3

Keywords

Search

Navigation