Skip to main content
SpringerLink
Log in

Regularized Pooling

  • Conference paper
  • First Online:
Artificial Neural Networks and Machine Learning – ICANN 2020 (ICANN 2020)

Part of the book series: Lecture Notes in Computer Science ((LNTCS,volume 12397))

Included in the following conference series:

Abstract

In convolutional neural networks (CNNs), pooling operations play important roles such as dimensionality reduction and deformation compensation. In general, max pooling, which is the most widely used operation for local pooling, is performed independently for each kernel. However, the deformation may be spatially smooth over the neighboring kernels. This means that max pooling is too flexible to compensate for actual deformations. In other words, its excessive flexibility risks canceling the essential spatial differences between classes. In this paper, we propose regularized pooling, which enables the value selection direction in the pooling operation to be spatially smooth across adjacent kernels so as to compensate only for actual deformations. The results of experiments on handwritten character images and texture images showed that regularized pooling not only improves recognition accuracy but also accelerates the convergence of learning compared with conventional pooling operations.

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 84.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 109.99
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

Notes

  1. 1.

    To be specific, given a convolutional feature map of size \(H \times W\) as input, \(I = \lfloor (H - 1)/s \rfloor + 1\) and \(J = \lfloor (W - 1)/s \rfloor + 1\) if we add a proper size of padding to the input.

  2. 2.

    If the fraction part is exactly 0.5, it is rounded away from zero.

References

  1. Aich, S., Stavness, I.: Global sum pooling: a generalization trick for object counting with small datasets of large images. In: Proceedings of CVPR Deep Vision Workshop (2019)

    Google Scholar 

  2. Bulo, S.R., Neuhold, G., Kontschieder, P.: Loss max-pooling for semantic image segmentation. In: Proceedings of CVPR, pp. 7082–7091 (2017)

    Google Scholar 

  3. Cohen, G., Afshar, S., Tapson, J., Van Schaik, A.: EMNIST: extending MNIST to handwritten letters. In: Proceedings of IJCNN, pp. 2921–2926 (2017)

    Google Scholar 

  4. Feng, J., Ni, B., Tian, Q., Yan, S.: Geometric \(l_p\)-norm feature pooling for image classification. In: Proceedings of CVPR, pp. 2609–2704 (2011)

    Google Scholar 

  5. Gao, Y., Beijbom, O., Zhang, N., Darrell, T.: Compact bilinear pooling. In: Proceedings of CVPR, pp. 317–326 (2016)

    Google Scholar 

  6. Gao, Z., Wang, L., Wu, G.: LIP: local importance-based pooling. In: Proceedings of ICCV, pp. 3355–3364 (2019)

    Google Scholar 

  7. Gong, Y., Wang, L., Guo, R., Lazebnik, S.: Multi-scale orderless pooling of deep convolutional activation features. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8695, pp. 392–407. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10584-0_26

    Chapter  Google Scholar 

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

  9. He, K., Zhang, X., Ren, S., Sun, J.: Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 37(9), 1904–1916 (2015)

    Article  Google Scholar 

  10. He, Y., Chiu, W.C., Keuper, M., Fritz, M.: STD2P: RGBD semantic segmentation using spatio-temporal data-driven pooling. In: Proceedings of CVPR, pp. 4837–4846 (2017)

    Google Scholar 

  11. Hinton, G.E., Srivastava, N., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.R.: Improving neural networks by preventing co-adaptation of feature detectors. arXiv preprint arXiv:1207.0580 (2012)

  12. Husain, S.S., Bober, M.: REMAP: multi-layer entropy-guided pooling of dense CNN features for image retrieval. IEEE Trans. Image Process. 28(10), 5201–5213 (2019)

    Article  MathSciNet  Google Scholar 

  13. Kobayashi, T.: Global feature guided local pooling. In: Proceedings of ICCV, pp. 3365–3374 (2019)

    Google Scholar 

  14. Kumar, A.: Ordinal pooling networks: for preserving information over shrinking feature maps. arXiv preprint arXiv:1804.02702 (2018)

  15. Kylberg, G.: The kylberg texture dataset v. 1.0. External report (blue series) 35. Centre for Image Analysis, Swedish University of Agricultural Sciences and Uppsala University, Uppsala, Sweden (2011). http://www.cb.uu.se/~gustaf/texture/

  16. Laptev, D., Savinov, N., Buhmann, J.M., Pollefeys, M.: TI-POOLING: transformation-invariant pooling for feature learning in convolutional neural networks. In: Proceedings of CVPR, pp. 289–297 (2016)

    Google Scholar 

  17. LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436–444 (2015)

    Article  Google Scholar 

  18. LeCun, Y., Bottou, L., Bengio, Y., Haffner, P., et al.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)

    Article  Google Scholar 

  19. Liu, J.J., Hou, Q., Cheng, M.M., Feng, J., Jiang, J.: A simple pooling-based design for real-time salient object detection. In: Proceedings of CVPR, pp. 3917–3926 (2019)

    Google Scholar 

  20. Nguyen, 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 

  21. Saeedan, F., Weber, N., Goesele, M., Roth, S.: Detail-preserving pooling in deep networks. In: Proceedings of CVPR, pp. 9108–9116 (2018)

    Google Scholar 

  22. Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: Proceedings of ICLR (2015)

    Google Scholar 

  23. Wan, L., Zeiler, M., Zhang, S., Le Cun, Y., Fergus, R.: Regularization of neural networks using dropconnect. In: Proceedings of ICML, pp. 1058–1066 (2013)

    Google Scholar 

  24. Wei, Z., et al.: Building detail-sensitive semantic segmentation networks with polynomial pooling. In: Proceedings of CVPR, pp. 7115–7123 (2019)

    Google Scholar 

  25. 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 

  26. Zhai, S., et al.: S3Pool: pooling with stochastic spatial sampling. In: Proceedings of CVPR, pp. 4970–4978 (2017)

    Google Scholar 

  27. Zhang, Y., Tang, S., Muandet, K., Jarvers, C., Neumann, H.: Local temporal bilinear pooling for fine-grained action parsing. In: Proceedings of CVPR, pp. 12005–12015 (2019)

    Google Scholar 

  28. Zheng, Y., Iwana, B.K., Uchida, S.: Mining the displacement of max-pooling for text recognition. Pattern Recogn. 93, 558–569 (2019)

    Article  Google Scholar 

Download references

Acknowledgments

This work was supported by JSPS KAKENHI Grant Number JP17H06100 and JST ACT-I Grant Number JPMJPR18UO.

Author information

Authors and Affiliations

  1. Kyushu University, Fukuoka, Japan

    Takato Otsuzuki, Hideaki Hayashi, Yuchen Zheng & Seiichi Uchida

Authors
  1. Takato Otsuzuki
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Hideaki Hayashi
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yuchen Zheng
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Seiichi Uchida
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Takato Otsuzuki or Hideaki Hayashi .

Editor information

Editors and Affiliations

  1. Department of Applied Informatics, Comenius University in Bratislava, Bratislava, Slovakia

    Igor Farkaš

  2. Department of Applied Mathematics and Computer Science, Technical University of Denmark, Kgs. Lyngby, Denmark

    Paolo Masulli

  3. Department of Informatics, University of Hamburg, Hamburg, Germany

    Stefan Wermter

Rights and permissions

Reprints and permissions

Copyright information

© 2020 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Otsuzuki, T., Hayashi, H., Zheng, Y., Uchida, S. (2020). Regularized Pooling. In: Farkaš, I., Masulli, P., Wermter, S. (eds) Artificial Neural Networks and Machine Learning – ICANN 2020. ICANN 2020. Lecture Notes in Computer Science(), vol 12397. Springer, Cham. https://doi.org/10.1007/978-3-030-61616-8_20

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-61616-8_20

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-61615-1

  • Online ISBN: 978-3-030-61616-8

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation