Skip to main content
Springer Nature Link
Log in

Co-Learning for Few-Shot Learning

  • Published:
Neural Processing Letters Aims and scope Submit manuscript

Abstract

Few-shot learning (FSL), aiming to address the problem of data scarcity, is a hot topic of current researches. The most commonly used FSL framework is composed of two components: (1) Pre-train. Employing the base data to train a feature extraction model (FEM). (2) Meta-test. Utilizing the trained FEM to extract novel data’s feature embedding and then recognize them with the to-be-designed classifier. Due to the constraint of limited labeled samples, some researchers attempt to exploit the unlabeled samples to strengthen the classifier by introducing self-training strategy. However, a single classifier (based on scarce labeled samples) usually incorrectly identifies unlabeled sample classes as its insufficient discrimination, which is dubbed as Single-Classifier-Misclassify-Data (SCMD) problem. To address this fundamental problem, we design a Co-learning (CL) method for FSL. Typically, we find that different classifiers have different adaptability to the same feature distribution. Hence we try to exploit two basic classifiers to separately infer pseudo-labels for unlabeled samples, and crossly expand them to the labeled data. The two complementary classifiers make the predicted accuracy more reliable. We evaluate our CL on five benchmark datasets (e.g., mini-ImageNet, tiered-ImageNet, CIFAR-FS, FC100, CUB), and can exceed other state-of-the-arts 0.63–4.6%. The outstanding performance has demonstrated the efficiency of our method.

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

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /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.

Institutional subscriptions

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

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

References

  1. Bertinetto L, Henriques JF, Torr P, Vedaldi A(2019) Meta-learning with differentiable closed-form solvers. In ICLR,

  2. Boudiaf M, Ziko IM, Jérôme R, José D, Pablo P, Ismail BA(2020). Transductive information maximization for few-shot learning, In NeurIPS

  3. Chapelle O, Scholkopf B, Zien A,Eds.(20096) Semi-supervised learning (chapelle, o. et al., eds.; 2006) [book reviews]. TNN, 20(3):542

  4. Chen C, Li K, Wei W, Joey TZ, Zeng Z(2020). Hierarchical graph neural networks for few-shot learning, TCSVT

  5. Chen W-Y, Liu Y-C, Kira Z, Yu-Chiang FW, Jia-Bin H(2019). A closer look at few-shot classification, In ICLR

  6. Fei-Fei Li, Fergus Rob, Perona Pietro (2006) One-shot learning of object categories. TPAMI 28(4):594–611

    Article  Google Scholar 

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

  8. Yanwei F, Hospedales TM, Xiang T, Gong S (2015) Transductive multi-view zero-shot learning. TPAMI 37(11):2332–2345

    Article  Google Scholar 

  9. Garcia V, Bruna J(2018) Few-shot learning with graph neural networks. In ICLR,

  10. Ghiasi G, Lin TY, Le QV(2018) Dropblock: a regularization method for convolutional networks. In NeurIPS,

  11. He K, Zhang X, Ren S, Sun J(2016) Deep residual learning for image recognition. In CVPR, pages 770–778,

  12. Hihn H, Braun DA (2020) Specialization in hierarchical learning systems. Neural Process Lett 52(3):2319–2352

    Article  Google Scholar 

  13. Shell XH, Pablo GM, Yang X, Xi S, Guillaume O, Neil DL, Andreas D (2020). Empirical bayes transductive meta-learning with synthetic gradients, In ICLR

  14. Jiang W, Huang K, Geng J, Deng X (2020) Multi-scale metric learning for few-shot learning. TCSVT 31(3):1091–1102

    Google Scholar 

  15. Joachims T(1999) Transductive inference for text classification using support vector machines. In ICML,

  16. Kim J, Kim H, Kim G(2020) Model-agnostic boundary-adversarial sampling for test-time generalization in few-shot learning. In European conference on computer vision , pages 599–617

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

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

  19. Krizhevsky A, Hinton G et al.(2009)Learning multiple layers of features from tiny images. Citeseer

  20. 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, pages 10657–10665

  21. 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, pages 1–10

  22. Li X, Sun Q, Liu Y, Zhou Q, Zheng S, Chua T-S, Schiele B (2019) Learning to self-train for semi-supervised few-shot classification. NeurIPS 32:10276–10286

    Google Scholar 

  23. Liu B, Cao Y, Lin Y, Li Q, Zhang Z, Long M, Hu H(2020) Negative margin matters: understanding margin in few-shot classification. In European conference on computer vision, pages 438–455

  24. Liu Y, Lee J, Park M, Kim S, Yang E, Sung Ju Hwang, and Yi Yang (2019). Transductive propagation network for few-shot learning. In ICLR, Learning to propagate labels

  25. Mangla P, Kumari N, Sinha A, Singh M, Krishnamurthy B, Balasubramanian VN(2020) Charting the right manifold: manifold mixup for few-shot learning. In Proceedings of the IEEE/CVF winter conference on applications of computer vision, pages 2218–2227

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

  27. Oreshkin B, López PR, Lacoste A(2018) Tadam: task dependent adaptive metric for improved few-shot learning. In NeurIPS, pages 721–731

  28. Qiao L, Shi Y, Li J, Wang Y, Huang T, Tian Y(2019) Transductive episodic-wise adaptive metric for few-shot learning. In Proceedings of the IEEE/CVF international conference on computer vision, pages 3603–3612

  29. Ravi S, Larochelle H(2016)Optimization as a model for few-shot learning. In ICLR

  30. Rodríguez P, Laradji I, Drouin A and Alexandre L(2020). Smoother manifold for few-shot classification. In European conference on computer vision , Embedding propagation

  31. Rosenberg C, Hebert M, Schneiderman H(2005) Semi-supervised self-training of object detection models. In WACV, volume 1

  32. Russakovsky Olga, Deng Jia, Hao Su, Krause Jonathan, Satheesh Sanjeev, Ma Sean, Huang Zhiheng, Karpathy Andrej, Khosla Aditya, Bernstein Michael et al (2015) Imagenet large scale visual recognition challenge. IJCV 115(3):211–252

    Article  MathSciNet  Google Scholar 

  33. Rusu AA, Rao D, Sygnowski J, Vinyals O, Pascanu R, Osindero S, Hadsell R(2019) Meta-learning with latent embedding optimization. In ICLR

  34. 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, pages 4193–4201

  35. Snell J, Swersky K, Zemel R(2017) Prototypical networks for few-shot learning. In NeurIPS, pages 4077–4087

  36. Srivastava Nitish, Hinton Geoffrey, Krizhevsky Alex, Sutskever Ilya, Salakhutdinov Ruslan (2014) Dropout: a simple way to prevent neural networks from overfitting. J Machine Learn Res 15(1):1929–1958

    MathSciNet  MATH  Google Scholar 

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

  38. Tseng H-Y, Lee H-Y, Huang J-B, Yang M-H(2020) Cross-domain few-shot classification via learned feature-wise transformation. In ICLR

  39. Verma V, Lamb A , Beckham C, Najafi A, Mitliagkas I, Lopez-Paz D, Bengio Y(2019) Manifold mixup: better representations by interpolating hidden states. In International conference on machine learning , pages 6438–6447

  40. Vinyals Oriol, Blundell Charles, Lillicrap Timothy, Wierstra Daan et al (2016) Matching networks for one shot learning. NeurIPS 29:3630–3638

    Google Scholar 

  41. Wang Q, Wang G, Kou G, Zang M, Wang H (2021) Application of meta-learning framework based on multiple-capsule intelligent neural systems in image classification. Neural Process Lett 54(3):2581–2602

    Article  Google Scholar 

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

  43. Xing C, Rostamzadeh N, Oreshkin B, Pinheiro PO (2019) Adaptive cross-modal few-shot learning. In Advances in neural information processing systems, pages 4847–4857

  44. Xu C, Liu C, Zhang L, Wang C, Li J, Huang F, Xue X, Fu Y(2021) Learning dynamic alignment via meta-filter for few-shot learning. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 5182–5191

  45. Yang L, Li L, Zhang Z, Zhou X, Zhou E, Liu Y(202) Dpgn: distribution propagation graph network for few-shot learning. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 13390–13399

  46. Yang S, Liu L and Min Xu, (2021) Distribution calibration. In International conference on machine learning, Free lunch for few-shot learning

  47. Yarowsky D(1995) Unsupervised word sense disambiguation rivaling supervised methods. In 33rd annual meeting of the association for computational linguistics, pages 189–196

  48. Yoon S W, Seo J, Moon J(2019) Tapnet: neural network augmented with task-adaptive projection for few-shot learning. In International conference on machine learning, pages 7115–7123

  49. Yu Z, Chen L , Cheng Z, Luo J(2020) Transmatch: a transfer-learning scheme for semi-supervised few-shot learning. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 12856–12864

  50. Ziko I, Dolz J, Granger E, Ayed I B(2020) Laplacian regularized few-shot learning. In International conference on machine learning, pages 11660–11670

Download references

Acknowledgements

The paper was supported by the National Natural Science Foundation of China (Grant No.61671480), the Open Project Program of the National Laboratory of Pattern Recognition (NLPR) (Grant No.202000009),the Major Scientific and Technological Projects of CNPC under Grant ZD2019-183-008, and the Graduate Innovation Project of China University of Petroleum (East China) YCX2021123.

Author information

Authors and Affiliations

  1. College of Control Science and Engineering, China University of Petroleum (East China), Qingdao, China

    Rui Xu, Shuai Shao, Baodi Liu & Weifeng Liu

  2. College of Oceanography and Space Informatics, China University of Petroleum (East China), Qingdao, China

    Lei Xing

  3. School of Petroleum Engineering, China University of Petroleum (East China), Qingdao, China

    Kai Zhang

  4. The State Key Laboratory of Integrated Services Networks, Xidian University, Xi’an, China

    Rui Xu & Weifeng Liu

Authors
  1. Rui Xu
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Lei Xing
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Shuai Shao
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Baodi Liu
    View author publications

    You can also search for this author inPubMed Google Scholar

  5. Kai Zhang
    View author publications

    You can also search for this author inPubMed Google Scholar

  6. Weifeng Liu
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Weifeng Liu.

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

Xu, R., Xing, L., Shao, S. et al. Co-Learning for Few-Shot Learning. Neural Process Lett 54, 3339–3356 (2022). https://doi.org/10.1007/s11063-022-10770-4

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11063-022-10770-4

Keywords