Does Removing Pooling Layers from Convolutional Neural Networks Improve Results? | SN Computer Science
Skip to main content
Springer Nature Link
Log in

Does Removing Pooling Layers from Convolutional Neural Networks Improve Results?

  • Original Research
  • Published:
SN Computer Science Aims and scope Submit manuscript

Abstract

Due to their number of parameters, convolutional neural networks are known to take long training periods and extended inference time. Learning may take so much computational power that it requires a costly machine and, sometimes, weeks for training. In this context, there is a trend already in motion to replace convolutional pooling layers for a stride operation in the previous layer to save time. In this work, we evaluate the speedup of such an approach and how it trades off with accuracy loss in multiple computer vision domains, deep neural architectures, and datasets. The results showed significant acceleration with an almost negligible loss in accuracy, when any, which is a further indication that convolutional pooling on deep learning performs redundant calculations.

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
¥17,985 /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 includes VAT (Japan)

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.

Notes

  1. http://rrc.cvc.uab.es/

  2. We used the Python OPF implementation available at https://github.com/marcoscleison/PyOPF.

References

  1. Abadi M, Agarwal A, Barham P, Brevdo E, Chen Z, Citro C, Corrado G.S, Davis A, Dean J, Devin M, Ghemawat S, Goodfellow I, Harp A, Irving G, Isard M, Jia Y, Jozefowicz R, Kaiser L, Kudlur M, Levenberg J, Mané D, Monga R, Moore S, Murray D, Olah C, Schuster M, Shlens J, Steiner B, Sutskever I, Talwar K, Tucker P, Vanhoucke V, Vasudevan V, Viégas F, Vinyals O, Warden P, Wattenberg M, Wicke M, Yu Y, Zheng X.: TensorFlow: large-scale machine learning on heterogeneous systems (2015). https://www.tensorflow.org/. Accessed 5 May 2020.

  2. Arganda-Carreras I, Turaga SC, Berger DR, Cireşan D, Giusti A, Gambardella LM, Schmidhuber J, Laptev D, Dwivedi S, Buhmann JM, et al. Crowdsourcing the creation of image segmentation algorithms for connectomics. Front Neuroanat. 2015;9:142.

    Article  Google Scholar 

  3. Cardona A, Saalfeld S, Preibisch S, Schmid B, Cheng A, Pulokas J, Tomancak P, Hartenstein V. An integrated micro-and macroarchitectural analysis of the drosophila brain by computer-assisted serial section electron microscopy. PLoS Biol. 2010;8(10):e1000502.

    Article  Google Scholar 

  4. Chen T, Li M, Li Y, Lin M, Wang N, Wang M, Xiao T, Xu B, Zhang C, Zhang Z. Mxnet: A flexible and efficient machine learning library for heterogeneous distributed systems. CoRR abs/1512.01274 (2015). http://arxiv.org/abs/1512.01274

  5. Chollet F, et al. Keras. (2015). https://keras.io. Accessed 5 May 2020.

  6. Cover TM, Hart PE, et al. Nearest neighbor pattern classification. IEEE Trans Inf Theory. 1967;13(1):21–7.

    Article  Google Scholar 

  7. DeVries T, Taylor G.W. Improved regularization of convolutional neural networks with cutout. arXiv preprint arXiv:1708.04552 (2017)

  8. Everingham M, Van Gool L, Williams CKI, Winn J, Zisserman A. The PASCAL Visual Object Classes Challenge 2007 (VOC2007) Results. http://www.pascal-network.org/challenges/VOC/voc2007/workshop/index.html. Accessed 5 May 2020.

  9. Ghiasi G, Lin TY, Le QV. Dropblock: a regularization method for convolutional networks. Advances in neural information processing systems. Cambridge: MIT Press; 2018. p. 10727–37.

    Google Scholar 

  10. Han J, Bhanu B. Individual recognition using gait energy image. IEEE Trans Pattern Anal Mach Intell. 2006;28(2):316–22.

    Article  Google Scholar 

  11. Harada T, Kuniyoshi Y. Graphical gaussian vector for image categorization. Advances in neural information processing systems. Cambridge: MIT Press; 2012. p. 1547–55.

    Google Scholar 

  12. Hubel D, Wiesel T. Receptive fields, binocular interaction, and functional architecture in the cat’s visual cortex. J Physiol. 1962;160:106–54.

    Article  Google Scholar 

  13. Hubel DH, Wiesel TN. Receptive fields of single neurons in the cat’s striate cortex. J Physiol. 1959;148:574–91.

    Article  Google Scholar 

  14. Hubel DH, Wiesel TN. Receptive fields and functional architecture in two nonstriate visual areas (18 and 19) of the cat. J Neurophysiol. 1965;28(2):229–89.

    Article  Google Scholar 

  15. Iwama H, Okumura M, Makihara Y, Yagi Y. The ou-isir gait database comprising the large population dataset and performance evaluation of gait recognition. IEEE Trans Inf Forensics Secur. 2012;7(5):1511–21.

    Article  Google Scholar 

  16. Jaderberg M, Simonyan K, Vedaldi A, Zisserman A. Reading text in the wild with convolutional neural networks. arXiv preprint arXiv:1412.1842 (2014)

  17. Jaderberg M, Simonyan K, Vedaldi A, Zisserman A. Synthetic data and artificial neural networks for natural scene text recognition. arXiv preprint arXiv:1406.2227 (2014)

  18. Jaderberg M, Simonyan K, Vedaldi A, Zisserman A. Reading text in the wild with convolutional neural networks. Int J Comput Vis. 2016;116(1):1–20.

    Article  MathSciNet  Google Scholar 

  19. Karatzas D, Gomez-Bigorda L, Nicolaou A, Ghosh S, Bagdanov A, Iwamura M, Matas J, Neumann L, Chandrasekhar V.R, Lu S. et al.: Icdar 2015 competition on robust reading. In: 2015 13th International conference on document analysis and recognition (ICDAR), IEEE, pp. 1156–1160 (2015)

  20. Krizhevsky A, Nair V, Hinton G. Cifar-10 (canadian institute for advanced research) 2009. http://www.cs.toronto.edu/~kriz/cifar.html. Accessed 5 May 2020.

  21. Krizhevsky A, Sutskever I, Hinton GE. Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems. Cambridge: MIT Press; 2012. p. 1097–105.

    Google Scholar 

  22. LeCun Y, Bottou L, Bengio Y, Haffner P. Gradient-based learning applied to document recognition. Proc IEEE. 1998;86(11):2278–324.

    Article  Google Scholar 

  23. LeCun Y, Cortes C. MNIST handwritten digit database. 2010. http://yann.lecun.com/exdb/mnist/. Accessed 5 May 2020.

  24. Lin M, Chen Q, Yan S. Network in network. CoRR abs/1312.4400 (2013). http://arxiv.org/abs/1312.4400

  25. Lin T, Maire M, Belongie S.J, Bourdev L.D, Girshick R.B, Hays J, Perona P, Ramanan D, Dollár P, Zitnick C.L. Microsoft COCO: common objects in context. CoRR abs/1405.0312 (2014). http://arxiv.org/abs/1405.0312

  26. Lowe DG. Distinctive image features from scale-invariant keypoints. Int J Comput Vis. 2004;60(2):91–110.

    Article  Google Scholar 

  27. Mnih V, Kavukcuoglu K, Silver D, Rusu AA, Veness J, Bellemare MG, Graves A, Riedmiller M, Fidjeland AK, Ostrovski G, Petersen S, Beattie C, Sadik A, Antonoglou I, King H, Kumaran D, Wierstra D, Legg S, Hassabis D. Human-level control through deep reinforcement learning. Nature. 2015;518(7540):529–33.

    Article  Google Scholar 

  28. Nagi J, Ducatelle F, Di Caro G.A, Cireşan D, Meier U, Giusti A, Nagi F, Schmidhuber J, Gambardella L.M. Max-pooling convolutional neural networks for vision-based hand gesture recognition. In: Signal and Image Processing Applications (ICSIPA), 2011 IEEE International Conference on, pp. 342–347. IEEE (2011)

  29. Netzer Y, Wang T, Coates A, Bissacco A, Wu B, Ng A.Y. Reading digits in natural images with unsupervised feature learning (2011)

  30. Papa JP, Falcão AX, Suzuki CTN. Supervised pattern classification based on optimum-path forest. Int J Imaging Syst Technol. 2009;19(2):120–31. https://doi.org/10.1002/ima.v19:2.

    Article  Google Scholar 

  31. Papa JP, Falcão AX, Albuquerque VHC, Tavares JMRS. Efficient supervised optimum-path forest classification for large datasets. Pattern Recogn. 2012;45(1):512–20.

    Article  Google Scholar 

  32. Paszke A, Gross S, Massa F, Lerer A, Bradbury J, Chanan G, Killeen T, Lin Z, Gimelshein N, Antiga L, Desmaison A, Kopf A, Yang E, DeVito Z, Raison M, Tejani A, Chilamkurthy S, Steiner B, Fang L, Bai J, Chintala S. Pytorch: an imperative style, high-performance deep learning library. Advances in neural Iinformation processing systems, vol. 32. New York: Curran Associates Inc; 2019. p. 8024–35.

    Google Scholar 

  33. Redmon J, Divvala S.K, Girshick R.B, Farhadi A. You only look once: Unified, real-time object detection. CoRR abs/1506.02640 (2015). http://arxiv.org/abs/1506.02640

  34. Redmon J, Farhadi A. YOLO9000: better, faster, stronger. CoRR abs/1612.08242 (2016). http://arxiv.org/abs/1612.08242

  35. Romera E, Alvarez J.M, Bergasa L.M, Arroyo R. Efficient convnet for real-time semantic segmentation. In: IEEE Intelligent Vehicles Symposium (IV), pp. 1789–1794 (2017)

  36. Ronneberger O, Fischer P, Brox T. U-net: Convolutional networks for biomedical image segmentation. CoRR abs/1505.04597 (2015)

  37. Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, Huang Z, Karpathy A, Khosla A, Bernstein M, Berg AC, Fei-Fei L. ImageNet large scale visual recognition challenge. Int J Comput Vis. 2015;115(3):211–52. https://doi.org/10.1007/s11263-015-0816-y.

    Article  MathSciNet  Google Scholar 

  38. Sánchez J, Perronnin F, Mensink T, Verbeek J. Image classification with the fisher vector: theory and practice. Int J Comput Vis. 2013;105(3):222–45.

    Article  MathSciNet  Google Scholar 

  39. do Santos CFG, Colombo D, Roder M, Papa JP. Maxdropout: Deep neural network regularization based on maximum output values (2020). arXiv:2007.13723.

  40. Santos CFG, Moreira TP, Colombo D, Papa JP. Does pooling really matter? an evaluation on gait recognition. In: Nyström A, Heredia YH, Núñez VM, editors. Progress in pattern recognition, image analysis, computer vision, and applications. Cham: Springer; 2019. p. 751–60.

    Chapter  Google Scholar 

  41. dos Santos CFG, Moreira TP, Colombo D, Papa JP. Does pooling really matter? an evaluation on gait recognition. Iberoamerican congress on pattern recognition. Berlin: Springer; 2019. p. 751–60.

    Google Scholar 

  42. Sermanet P, Eigen D, Zhang X, Mathieu M, Fergus R, LeCun Y. Overfeat: Integrated recognition, localization and detection using convolutional networks. arXiv preprint arXiv:1312.6229 (2013)

  43. Shahab A, Shafait F, Dengel A. Icdar 2011 robust reading competition challenge 2: Reading text in scene images. In: 2011 International conference on document analysis and recognition, IEEE, pp. 1491–1496 (2011)

  44. Shiraga K, Makihara Y, Muramatsu D, Echigo T, Yagi Y. Geinet: View-invariant gait recognition using a convolutional neural network. In: 2016 International conference on biometrics (ICB), IEEE, pp. 1–8 (2016)

  45. Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)

  46. Torralba A, Fergus R, Freeman WT. 80 million tiny images: a large data set for nonparametric object and scene recognition. IEEE Trans Pattern Anal Mach Intell. 2008;30(11):1958–70. https://doi.org/10.1109/TPAMI.2008.128.

    Article  Google Scholar 

  47. Wilcoxon F. Individual comparisons by ranking methods. Biometrics Bull. 1945;1(6):80–3.

    Article  Google Scholar 

  48. Zeiler M.D, Fergus R. Visualizing and understanding convolutional networks. In: European conference on computer vision, Springer, pp. 818–833 (2014)

  49. Zhang Y, Gueguen L, Zharkov I, Zhang P, Seifert K, Kadlec B. Uber-text: A large-scale dataset for optical character recognition from street-level imagery. In: SUNw: Scene Understanding Workshop—CVPR 2017. Hawaii, USA (2017)

  50. Zhong Z, Zheng L, Kang G, Li S, Yang Y. Random erasing data augmentation. In: Proceedings of the AAAI Conference on Artificial Intelligence (AAAI) (2020)

Download references

Acknowledgements

The authors are grateful to Petrobras grant #2017/00285-6, FAPESP grants #2013/07375-0, #2014/12236-1, #2017/25908-6, #2018/15597-6, #2019/07665-4, as well as CNPq grants #307066/2017-7 and #427968/2018-6. On behalf of all authors, the corresponding author states that there is no conflict of interest.

Author information

Authors and Affiliations

  1. UFSCar, Federal University of São Carlos, São Carlos, Brazil

    Claudio Filipi Goncalves dos Santos

  2. UNESP, State University of Sao Paulo, Bauru, Brazil

    Thierry Pinheiro Moreira & João Paulo Papa

  3. Cenpes, Petróleo Brasileiro S.A., Petrobras, Rio de Janeiro, RJ, Brazil

    Danilo Colombo

Authors
  1. Claudio Filipi Goncalves dos Santos
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Thierry Pinheiro Moreira
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Danilo Colombo
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. João Paulo Papa
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Claudio Filipi Goncalves dos Santos.

Ethics declarations

Conflicts of interest

The authors declare that they have no conflict of interest.

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

Santos, C.F.G.d., Moreira, T.P., Colombo, D. et al. Does Removing Pooling Layers from Convolutional Neural Networks Improve Results?. SN COMPUT. SCI. 1, 275 (2020). https://doi.org/10.1007/s42979-020-00295-9

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s42979-020-00295-9

Keywords

Search

Navigation