Skip to main content
SpringerLink
Log in

Meta-learning of Pooling Layers for Character Recognition

  • Conference paper
  • First Online:
Document Analysis and Recognition – ICDAR 2021 (ICDAR 2021)

Part of the book series: Lecture Notes in Computer Science ((LNIP,volume 12823))

Included in the following conference series:

Abstract

In convolutional neural network-based character recognition, pooling layers play an important role in dimensionality reduction and deformation compensation. However, their kernel shapes and pooling operations are empirically predetermined; typically, a fixed-size square kernel shape and max pooling operation are used. In this paper, we propose a meta-learning framework for pooling layers. As part of our framework, a parameterized pooling layer is proposed in which the kernel shape and pooling operation are trainable using two parameters, thereby allowing flexible pooling of the input data. We also propose a meta-learning algorithm for the parameterized pooling layer, which allows us to acquire a suitable pooling layer across multiple tasks. In the experiment, we applied the proposed meta-learning framework to character recognition tasks. The results demonstrate that a pooling layer that is suitable across character recognition tasks was obtained via meta-learning, and the obtained pooling layer improved the performance of the model in both few-shot character recognition and noisy image recognition tasks.

We provide our implementation at https://github.com/Otsuzuki/Meta-learning-of-Pooling-Layers-for-Character-Recognition.

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

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Baik, S., Hong, S., Lee, K.M.: Learning to forget for meta-learning. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2379–2387 (2020)

    Google Scholar 

  2. Berman, M., Jégou, H., Vedaldi, A., Kokkinos, I., Douze, M.: Multigrain: a unified image embedding for classes and instances. arXiv preprint arXiv:1902.05509 (2019)

  3. Chen, J., Zhan, L.M., Wu, X.M., Chung, F.l.: Variational metric scaling for metric-based meta-learning. In: AAAI Conference on Artificial Intelligence, vol. 34, pp. 3478–3485 (2020)

    Google Scholar 

  4. Cui, Y., Zhou, F., Wang, J., Liu, X., Lin, Y., Belongie, S.: Kernel pooling for convolutional neural networks. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2921–2930 (2017)

    Google Scholar 

  5. Dollar, P., Tu, Z., Perona, P., Belongie, S.: Integral channel features. In: British Machine Vision Conference (2009)

    Google Scholar 

  6. Elsken, T., Staffler, B., Metzen, J.H., Hutter, F.: Meta-learning of neural architectures for few-shot learning. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 12365–12375 (2020)

    Google Scholar 

  7. Feng, J., Ni, B., Tian, Q., Yan, S.: Geometric \(l_p\)-norm feature pooling for image classification. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2609–2704 (2011)

    Google Scholar 

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

    Google Scholar 

  9. Gao, Y., Beijbom, O., Zhang, N., Darrell, T.: Compact bilinear pooling. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 317–326 (2016)

    Google Scholar 

  10. Gao, Z., Xie, J., Wang, Q., Li, P.: Global second-order pooling convolutional networks. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3024–3033 (2019)

    Google Scholar 

  11. Gao, Z., Wang, L., Wu, G.: LIP: local importance-based pooling. In: International Conference on Computer Vision, pp. 3355–3364 (2019)

    Google Scholar 

  12. Graham, B.: Fractional max-pooling. arXiv preprint arXiv:1412.6071 (2014)

  13. Hou, Q., Zhang, L., Cheng, M.M., Feng, J.: Strip pooling: rethinking spatial pooling for scene parsing. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 4003–4012 (2020)

    Google Scholar 

  14. Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine Learning, pp. 448–456 (2015)

    Google Scholar 

  15. Khodadadeh, S., Bölöni, L., Shah, M.: Unsupervised meta-learning for few-shot image classification. In: Advances in Neural Information Processing Systems, vol. 32 (2019)

    Google Scholar 

  16. Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: International Conference on Learning Representations (2015)

    Google Scholar 

  17. Lake, B.M., Salakhutdinov, R., Tenenbaum, J.B.: The Omniglot challenge: a 3-year progress report. Curr. Opin. Behav. Sci. 29, 97–104 (2019)

    Article  Google Scholar 

  18. Li, P., Xie, J., Wang, Q., Gao, Z.: Towards faster training of global covariance pooling networks by iterative matrix square root normalization. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 947–955 (2018)

    Google Scholar 

  19. Lin, T.Y., RoyChowdhury, A., Maji, S.: Bilinear CNN models for fine-grained visual recognition. In: IEEE International Conference on Computer Vision, pp. 1449–1457 (2015)

    Google Scholar 

  20. Malinowski, M., Fritz, M.: Learning smooth pooling regions for visual recognition. In: British Machine Vision Conference (2013)

    Google Scholar 

  21. Munkhdalai, T., Yu, H.: Meta networks. In: International Conference on Machine Learning, pp. 2554–2563 (2017)

    Google Scholar 

  22. NguyenVan, D., Lu, S., Tian, S., Ouarti, N., Mokhtari, M.: A pooling based scene text proposal technique for scene text reading in the wild. Pattern Recogn. 87, 118–129 (2019)

    Article  Google Scholar 

  23. Otsuzuki, T., Hayashi, H., Zheng, Y., Uchida, S.: Regularized pooling. In: Farkaš, I., Masulli, P., Wermter, S. (eds.) ICANN 2020. LNCS, vol. 12397, pp. 241–254. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-61616-8_20

    Chapter  Google Scholar 

  24. Rusu, A.A., et al.: Meta-learning with latent embedding optimization. In: International Conference on Learning Representations (2019)

    Google Scholar 

  25. Saeedan, F., Weber, N., Goesele, M., Roth, S.: Detail-preserving pooling in deep networks. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 9108–9116 (2018)

    Google Scholar 

  26. Santoro, A., Bartunov, S., Botvinick, M., Wierstra, D., Lillicrap, T.: Meta-learning with memory-augmented neural networks. In: International Conference on Machine Learning, vol. 48, pp. 1842–1850 (2016)

    Google Scholar 

  27. Sermanet, P., Chintala, S., LeCun, Y.: Convolutional neural networks applied to house numbers digit classification. In: International Conference on Pattern Recognition, pp. 3288–3291 (2012)

    Google Scholar 

  28. Sung, F., Yang, Y., Zhang, L., Xiang, T., Torr, P.H., Hospedales, T.M.: Learning to compare: relation network for few-shot learning. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1199–1208 (2018)

    Google Scholar 

  29. Tolias, G., Sicre, R., Jégou, H.: Particular object retrieval with integral max-pooling of CNN activations. In: International Conference on Learning Representations (2016)

    Google Scholar 

  30. Vinyals, O., Blundell, C., Lillicrap, T., Kavukcuoglu, K., Wierstra, D.: Matching networks for one shot learning. In: Advances in Neural Information Processing Systems, vol. 29, pp. 3630–3638 (2016)

    Google Scholar 

  31. Wang, H., Wang, Q., Gao, M., Li, P., Zuo, W.: Multi-scale location-aware kernel representation for object detection. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1248–1257 (2018)

    Google Scholar 

  32. Wei, Z., et al.: Building detail-sensitive semantic segmentation networks with polynomial pooling. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 7115–7123 (2019)

    Google Scholar 

  33. Yu, D., Wang, H., Chen, P., Wei, Z.: Mixed pooling for convolutional neural networks. In: Miao, D., Pedrycz, W., Ślȩzak, D., Peters, G., Hu, Q., Wang, R. (eds.) RSKT 2014. LNCS (LNAI), vol. 8818, pp. 364–375. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-11740-9_34

    Chapter  Google Scholar 

  34. Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2881–2890 (2017)

    Google Scholar 

  35. Zhou, A., Knowles, T., Finn, C.: Meta-learning symmetries by reparameterization. In: International Conference on Learning Representations (2021)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Kyushu University, Fukuoka, Japan

    Takato Otsuzuki, Heon Song, Seiichi Uchida & Hideaki Hayashi

Authors
  1. Takato Otsuzuki
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Heon Song
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Seiichi Uchida
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Hideaki Hayashi
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Hideaki Hayashi .

Editor information

Editors and Affiliations

  1. Universitat Autònoma de Barcelona, Barcelona, Spain

    Josep Lladós

  2. Lehigh University, Bethlehem, PA, USA

    Daniel Lopresti

  3. Kyushu University, Fukuoka-shi, Japan

    Seiichi Uchida

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

Otsuzuki, T., Song, H., Uchida, S., Hayashi, H. (2021). Meta-learning of Pooling Layers for Character Recognition. In: Lladós, J., Lopresti, D., Uchida, S. (eds) Document Analysis and Recognition – ICDAR 2021. ICDAR 2021. Lecture Notes in Computer Science(), vol 12823. Springer, Cham. https://doi.org/10.1007/978-3-030-86334-0_13

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-86334-0_13

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-86333-3

  • Online ISBN: 978-3-030-86334-0

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Societies and partnerships

Search

Navigation