Skip to main content

Advertisement

Springer Nature Link
Log in

Meta-BN Net for few-shot learning

  • Research Article
  • Published:
Frontiers of Computer Science Aims and scope Submit manuscript

Abstract

In this paper, we propose a lightweight network with an adaptive batch normalization module, called Meta-BN Net, for few-shot classification. Unlike existing few-shot learning methods, which consist of complex models or algorithms, our approach extends batch normalization, an essential part of current deep neural network training, whose potential has not been fully explored. In particular, a meta-module is introduced to learn to generate more powerful affine transformation parameters, known as σ and β, in the batch normalization layer adaptively so that the representation ability of batch normalization can be activated. The experimental results on miniImageNet demonstrate that Meta-BN Net not only outperforms the baseline methods at a large margin but also is competitive with recent state-of-the-art few-shot learning methods. We also conduct experiments on Fewshot-CIFAR100 and CUB datasets, and the results show that our approach is effective to boost the performance of weak baseline networks. We believe our findings can motivate to explore the undiscovered capacity of base components in a neural network as well as more efficient few-shot learning methods.

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

Similar content being viewed by others

References

  1. Krizhevsky A, Sutskever I, Hinton G E. Imagenet classification with deep convolutional neural networks. In: Proceedings of the 26th Conference on Neural Information Processing Systems. 2012, 1106–1114

  2. Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. In: Proceedings of the 3rd International Conference on Learning Representations. 2015

  3. Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A. Going deeper with convolutions. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. 2015, 1–9

  4. He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. 2016, 770–778

  5. Lake B M, Salakhutdinov R, Tenenbaum J B. Human-level concept learning through probabilistic program induction. Science, 2015, 350(6266): 1332–1338

    Article  MathSciNet  Google Scholar 

  6. Fei-Fei L, Fergus R, Perona P. One-shot learning of object categories. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006, 28(4): 594–611

    Article  Google Scholar 

  7. Vinyals O, Blundell C, Lillicrap T, Kavukcuoglu K, Wierstra D. Matching networks for one shot learning. In: Proceedings of the 30th International Conference on Neural Information Processing Systems. 2016, 3637–3645

  8. Tian Y, Wang Y, Krishnan D, Tenenbaum J B, Isola P. Rethinking few-shot image classification: a good embedding is all you need? In: Proceedings of the 16th European Conference on Computer Vision. 2020, 266–282

  9. Goldblum M, Reich S, Fowl L, Ni R, Cherepanova V, Goldstein T. Unraveling meta-learning: understanding feature representations for few-shot tasks. In: Proceedings of the 37th International Conference on Machine Learning. 2020, 3607–3616

  10. Bendre N, Marín H T, Najafirad P. Learning from few samples: a survey. 2020, arXiv preprint arXiv: 2007.15484

  11. Bengio Y, Bengio S, Cloutier J. Learning a synaptic learning rule. In: Proceedings of IJCNN-91-Seattle International Joint Conference on Neural Networks. 1991, 969

  12. Schmidhuber J. Evolutionary principles in self-referential learning. On learning now to learn: the meta-meta-meta…-hook. Technische Universitat Munchen, Dissertation, 1987

  13. Chen W Y, Liu Y C, Kira Z, Wang Y C F, Huang J B. A closer look at few-shot classification. In: Proceedings of the 7th International Conference on Learning Representations. 2019

  14. Bronskill J, Gordon J, Requeima J, Nowozin S, Turner R E. TASKNORM: rethinking batch normalization for meta-learning. In: Proceedings of the 37th International Conference on Machine Learning. 2020, 1153–1164

  15. Ba J L, Kiros J R, Hinton G E. Layer normalization. 2016, arXiv preprint arXiv: 1607.06450

  16. Ulyanov D, Vedaldi A, Lempitsky V. Instance normalization: the missing ingredient for fast stylization. 2016, arXiv preprint arXiv: 1607.08022

  17. Ioffe S, Szegedy C. Batch normalization: accelerating deep network training by reducing internal covariate shift. In: Proceedings of the 32nd International Conference on Machine Learning. 2015, 448–456

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

  19. Graves A, Wayne G, Danihelka I. Neural turing machines. 2014, arXiv preprint arXiv: 1410.5401

  20. Mishra N, Rohaninejad M, Chen X, Abbeel P. A simple neural attentive meta-learner. In: Proceedings of the 6th International Conference on Learning Representations. 2018

  21. Finn C, Abbeel P, Levine S. Model-agnostic meta-learning for fast adaptation of deep networks. In: Proceedings of the 34th International Conference on Machine Learning. 2017, 1126–1135

  22. Li Z G, Zhou F W, Chen F, Li H. Meta-SGD: learning to learn quickly for few-shot learning. 2017, arXiv preprint arXiv: 1707.09835

  23. Nichol A, Achiam J, Schulman J. On first-order meta-learning algorithms. 2018, arXiv preprint arXiv: 1803.02999

  24. Jamal M A, Qi G J. Task agnostic meta-learning for few-shot learning. In: Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2019, 11711–11719

  25. Snell J, Swersky K, Zemel R. Prototypical networks for few-shot learning. In: Proceedings of the 31st International Conference on Neural Information Processing Systems. 2017, 4080–4090

  26. Gidaris S, Komodakis N. Dynamic few-shot visual learning without forgetting. In: Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2018, 4367–4375

  27. Dhillon G S, Chaudhari P, Ravichandran A, Soatto S. A baseline for few-shot image classification. In: Proceedings of the 8th International Conference on Learning Representations. 2020

  28. Wang Y, Chao W L, Weinberger K Q, van der Maaten L. SimpleShot: revisiting nearest-neighbor classification for few-shot learning. 2019, arXiv preprint arXiv: 1911.04623

  29. de Vries H, Strub F, Mary J, Larochelle H, Pietquin O, Courville A. Modulating early visual processing by language. In: Proceedings of the 31st International Conference on Neural Information Processing Systems. 2017, 6597–6607

  30. Dumoulin V, Shlens J, Kudlur M. A learned representation for artistic style. In: Proceedings of the 5th International Conference on Learning Representations. 2017

  31. Huang X, Belongie S. Arbitrary style transfer in real-time with adaptive instance normalization. In: Proceedings of IEEE International Conference on Computer Vision. 2017, 1510–1519

  32. Park T, Liu M Y, Wang T C, Zhu J Y. Semantic image synthesis with spatially-adaptive normalization. In: Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2019, 2332–2341

  33. Oreshkin B N, Rodriguez P, Lacoste A. TADAM: task dependent adaptive metric for improved few-shot learning. In: Proceedings of the 32nd International Conference on Neural Information Processing Systems. 2018, 719–729

  34. Perez E, Strub F, de Vries H, Dumoulin V, Courville A. FiLM: visual reasoning with a general conditioning layer. In: Proceedings of the 32nd AAAI Conference on Artificial Intelligence. 2018, 3942–3951

  35. Tseng H Y, Lee H Y, Huang J B, Yang M H. Cross-domain few-shot classification via learned feature-wise transformation. In: Proceedings of International Conference on Learning Representations. 2020

  36. Guo Y, Codella N C, Karlinsky L, Codella J V, Smith J R, Saenko K, Rosing T, Feris R. A broader study of cross-domain few-shot learning. In: Proceedings of the 16th European Conference on Computer Vision. 2020, 124–141

  37. Requeima J, Gordon J, Bronskill J, Nowozin S, Turner R E. Fast and flexible multi-task classification using conditional neural adaptive processes. In: Proceedings of the 33rd International Conference on Neural Information Processing Systems. 2019, 7957–7968

  38. Howard A G, Zhu M L, Chen B, Kalenichenko D, Wang W J, Weyand T, Andreetto M, Adam H. MobileNets: efficient convolutional neural networks for mobile vision applications. 2016, arXiv preprint arXiv: 1704.04861

  39. Wah C, Branson S, Welinder P, Perona P, Belongie S. The Caltech-UCSD birds-200–2011 dataset. Technical Report CNS-TR-2011–001. Pasadena, CA, USA: California Institute of Technology, 2011

    Google Scholar 

  40. Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, Huang Z, Karpathy A, Khosla A, Bernstein M, Berg A C, Fei-Fei L. ImageNet large scale visual recognition challenge. International Journal of Computer Vision, 2015, 115(3): 211–252

    Article  MathSciNet  Google Scholar 

  41. Ravi S, Larochelle H. Optimization as a model for few-shot learning. In: Proceedings of the 5th International Conference on Learning Representations. 2017

  42. Krizhevsky A, Hinton G. Learning multiple layers of features from tiny images. University of Toronto, Dissertation, 2009

  43. Hilliard N, Phillips L, Howland S, Yankov A, Corley C D, Hodas N O. Few-shot learning with metric-agnostic conditional embeddings. 2018, arXiv preprint arXiv: 1802.04376

  44. Satorras V G, Estrach J B. Few-shot learning with graph neural networks. In: Proceedings of the 6th International Conference on Learning Representations. 2018

  45. Sung F, Yang Y, Zhang L, Xiang T, Torr P H S, Hospedales T M. Learning to compare: relation network for few-shot learning. In: Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2018, 1199–1208

  46. Qiao S, Liu C, Shen W, Yuille A. Few-shot image recognition by predicting parameters from activations. In: Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2018, 7229–7238

  47. Ye H J, Hu H, Zhan D C, Sha F. Few-shot learning via embedding adaptation with set-to-set functions. 2018, arXiv preprint arXiv: 1812.03664

  48. Jiang X, Havaei M, Varno F, Chartrand G, Chapados N, Matwin S. Learning to learn with conditional class dependencies. In: Proceedings of the 7th International Conference on Learning Representations. 2019

  49. Xing C, Rostamzadeh N, Oreshkin B N, Pinheiro P O. Adaptive cross-modal few-shot learning. In: Proceedings of International Conference on Neural Information Processing Systems. 2019, 4848–4858

  50. Zhang C, Cai Y, Lin G, Shen C. DeepEMD: few-shot image classification with differentiable earth mover’s distance and structured classifiers. In: Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020, 12200–12210

  51. Rusu A A, Rao D, Sygnowski J, Vinyals O, Pascanu R, Osindero S, Hadsell R. Meta-learning with latent embedding optimization. In: Proceedings of the 7th International Conference on Learning Representations. 2019

  52. Rodríguez P, Laradji I, Drouin A, Lacoste A. Embedding propagation: smoother manifold for few-shot classification. In: Proceedings of the 16th European Conference on Computer Vision. 2020, 121–138

  53. Hu S X, Moreno P G, Xiao Y, Shen X, Obozinski G, Lawrence N D, Damianou A C. Empirical Bayes transductive meta-learning with synthetic gradients. In: Proceedings of the 8th International Conference on Learning Representations. 2020

  54. Davies D L, Bouldin D W. A cluster separation measure. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1979, 1(2): 224–227

    Article  Google Scholar 

Download references

Acknowledgements

This work was supported by the National Natural Science Foundation of China (Grant Nos. 61673396, U19A2073, 61976245).

Author information

Authors and Affiliations

  1. School of Computer Science, China University of Petroleum, Qingdao, 266580, China

    Wei Gao, Mingwen Shao & Xinkai Zhuang

  2. School of Mathematics and Statistics, Xi’an Jiaotong University, Xi’an, 710049, China

    Jun Shu

Authors
  1. Wei Gao
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Mingwen Shao
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Jun Shu
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Xinkai Zhuang
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Mingwen Shao.

Additional information

Wei Gao received the bachelor’s degree from the College of Computer Science and Technology, China University of Petroleum, China in 2019 and is currently a MS at China University of Petroleum, China under the supervision of Prof. Shao. His current research interests include few-shot learning and meta-learning.

Mingwen Shao received his MS degree in mathematics from the Guangxi University, China in 2002, and the PhD degree in applied mathematics from Xi’an Jiaotong University, China in 2005. He received the postdoctoral degree in control science and engineering from Tsinghua University, China in 2008. Now he is a professor and doctoral supervisor at China University of Petroleum, China. His research interests include data mining, machine learning and generative adversarial learning.

Jun Shu is currently a PhD candidate at Xi’an Jiaotong University, China under the supervision of Prof. Deyu Meng and Prof. Zongben Xu. His current research interests include machine learning and computer vision, especially on small sample learning, learning to learn and meta learning.

Xinkai Zhuang is currently a master student at China University of Petroleum, China under the supervision of Prof. Mingwen Shao. His current research interests include machine learning and computer vision, especially on few shot learning, transfer learning and meta learning.

Electronic supplementary material

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Gao, W., Shao, M., Shu, J. et al. Meta-BN Net for few-shot learning. Front. Comput. Sci. 17, 171302 (2023). https://doi.org/10.1007/s11704-021-1237-4

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s11704-021-1237-4

Keywords