Skip to main content

Integrating Task Information into Few-Shot Classifier by Channel Attention

  • Conference paper
  • First Online:
Knowledge Science, Engineering and Management (KSEM 2021)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 12817))

  • 2222 Accesses

Abstract

It has been increasingly recognized that meta-learning-based approaches provide a promising way to handle challenges to few-shot learning. In this paper, we incorporate the channel attention in the main framework of simple-CNAPS proposed by Bateni et al. to develop a model more appropriate for few-shot image classification. In detail, we replace FiLM layers in simple-CNAPS with channel attention blocks which scale the image channels according to the relationship between task information and feature maps rather than only the task information. This replacement makes the feature extractor more expressive. Moreover, it allows us to take the interaction of different image channels into account. In addition, to alleviate the computational bias caused by small sample size, we provide a method to estimate class centers with perturbations. Finally, the effectiveness of the model is verified by experiments on the few-shot image classification benchmark datasets.

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

Access this chapter

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

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: 27th International Conference on Neural Information Processing Systems (NeurIPS), pp. 3104–3112. MIT, Montreal (2014)

    Google Scholar 

  2. He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770–778. IEEE, Las Vegas (2016)

    Google Scholar 

  3. Chen, M., Zhang, Y., Qiu, M., Guizani, N., Hao, Y.: SPHA: smart personal health advisor based on deep analytics. IEEE Commun. Mag. 56(3), 164–169 (2018)

    Article  Google Scholar 

  4. Ren, M., Triantafillou, E., Ravi, S., Snell, J., et al.: Meta learning for semi-supervised few-shot classification. CoRR, abs/1803.00676(2018)

    Google Scholar 

  5. Esteva, A., et al.: Dermatologist-level classification of skin cancer with deep neural networks. Nature 542(7639), 115–118 (2017)

    Article  Google Scholar 

  6. Finn, C., Abbeel, P., Levine, S.: Model-agnostic meta-learning for fast adaptation of deep networks. In: 34th International Conference on Machine Learning, pp. 1126–1135. JMLR, Sydney (2017)

    Google Scholar 

  7. Hospedales, T., Antoniou, A., Micaelli, P., Storkey, A.: Meta-learning in neural networks: a survey. arXiv preprint arXiv:2004.05439 (2020)

  8. Rajeswaran, A., Finn, C., Kakade, S.M., Levine, S.: Meta-learning with implicit gradients. In: 33rd Conference on Neural Information Processing Systems (NeurIPS), pp. 113–124. MIT, Vancouver (2019)

    Google Scholar 

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

  10. Ravi, S., Larochelle, H.: Optimization as a model for few shot learning. In: 5th International Conference on Learning Representations (ICLR), OpenReview.net, Toulon (2016)

    Google Scholar 

  11. Mishra, N., Rohaninejad, M., Chen, X., Abbeel, P.: A simple neural attentive meta-learner. In: 6th International Conference on Learning Representations (ICLR), OpenReview.net, Vancouver (2018)

    Google Scholar 

  12. Vinyals, O., Blundell, C., Lillicrap, T., Wierstra, D., et al.: Matching networks for one shot learning. In: 29th Annual Conference on Neural Information Processing Systems (NeurIPS), pp. 3630–3638. MIT, Barcelona (2016)

    Google Scholar 

  13. Snell, J., Swersky, K., Zemel, R.: Prototypical networks for few-shot learning. In: 30rd Annual Conference on Neural Information Processing Systems (NeurIPS), Long Beach, USA, pp. 4077–4087 (2017)

    Google Scholar 

  14. Tian, Y., Wang, Y., Krishnan, D., Tenenbaum, J.B., Isola, P.: Rethinking few-shot image classification: a good embedding is all you need? In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12359, pp. 266–282. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58568-6_16

    Chapter  Google Scholar 

  15. Requeima, J., Gordon, J., Bronskill, J., Nowozin, S., Turner, R.E.: Fast and flexible multi-task classification using conditional neural adaptive processes. In: 32rd Conference on Neural Information Processing Systems(NeurIPS), Vancouver, Canada, pp. 7957–7968 (2019)

    Google Scholar 

  16. Perez, E., Strub, F., Vries, H.D., Dumoulin, V., Courville, A.: FiLM: visual reasoning with a general conditioning layer. In: 32nd AAAI Conference on Artificial Intelligence (AAAI), pp. 3942–3951. AAAI press, New Orleans (2018)

    Google Scholar 

  17. Bateni, P., Goyal, R., Masrani, V., Wood, F., Sigal, L.: Improved few-shot visual classification. In: 2020 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 14481–14490. IEEE, Seattle (2020)

    Google Scholar 

  18. Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: 2018 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7132–7141. IEEE, Salt Lake City (2018)

    Google Scholar 

  19. Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)

    Article  Google Scholar 

  20. Chen, J., Wu, X., Li, Y., Li, Q., Zhan, L., Chung, F.: A closer look at the training strategy for modern meta-learning. In: 33th International Conference on Neural Information Processing Systems (NeurIPS). Virtual (2020)

    Google Scholar 

  21. Chen, Y., et al.: Modular meta-learning with shrinkage. In: 33th International Conference on Neural Information Processing Systems (NeurIPS). Virtual (2020)

    Google Scholar 

  22. Lu, J., Gong, P., Ye, J.: Learning from very few samples: a survey. CoRR: abs/2009.02653 (2020)

    Google Scholar 

  23. Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. 115(3), 211–252 (2015)

    Article  MathSciNet  Google Scholar 

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

    Article  MathSciNet  Google Scholar 

  25. Triantafillou, E., et al.: Meta-dataset: a dataset of datasets for learning to learn from examples. In: 8th International Conference on Learning Representations (ICLR). OpenReview.net, Addis Ababa (2020)

    Google Scholar 

  26. Oreshkin, B., Rodrıguez Lopez, P., Lacoste, A.: TADAM: task dependent adaptive metric for improved few-shot learning. In: 31st Annual Conference on Neural Information Processing Systems (NeurIPS), Montreal, Canada, pp. 721–731 (2018)

    Google Scholar 

  27. Liu, Y., Lee, J., Park, M., Kim, S., Yang, Y.: Transductive propagation network for few-shot learning. CoRR, abs/1805.10002 (2018)

    Google Scholar 

  28. Rusu, A.A., et al.: Meta-learning with latent embedding optimization. CoRR, abs/1807.05960 (2018)

    Google Scholar 

Download references

Acknowledgements

This work was partly supported by the National Natural Science Foundation of China under Grant No. 61572002, No. 61690201, and No. 61732001.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Zhaochen Li .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2021 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Li, Z., Mu, K. (2021). Integrating Task Information into Few-Shot Classifier by Channel Attention. In: Qiu, H., Zhang, C., Fei, Z., Qiu, M., Kung, SY. (eds) Knowledge Science, Engineering and Management. KSEM 2021. Lecture Notes in Computer Science(), vol 12817. Springer, Cham. https://doi.org/10.1007/978-3-030-82153-1_12

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-82153-1_12

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-82152-4

  • Online ISBN: 978-3-030-82153-1

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics