Multiple Wavelet Pooling for CNNs

  • Aina FerràEmail author
  • Eduardo Aguilar
  • Petia Radeva
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11132)


Pooling layers are an essential part of any Convolutional Neural Network. The most popular pooling methods, as max pooling or average pooling, are based on a neighborhood approach that can be too simple and easily introduce visual distortion. To tackle these problems, recently a pooling method based on Haar wavelet transform was proposed. Following the same line of research, in this work, we explore the use of more sophisticated wavelet transforms (Coiflet, Daubechies) to perform the pooling. Additionally, considering that wavelets work similarly to filters, we propose a new pooling method for Convolutional Neural Network that combines multiple wavelet transforms. The results achieved demonstrate the benefits of our approach, improving the performance on different public object recognition datasets.


Wavelet CNN Pooling functions Object recognition 



This work was partially funded by TIN2015-66951-C2-1-R, 2017 SGR 1742, Nestore, 20141510 (La MaratoTV3) and CERCA Programme/Generalitat de Catalunya. E. Aguilar acknowledges the support of CONICYT Becas Chile. P. Radeva is partially supported by ICREA Academia 2014. We acknowledge the support of NVIDIA Corporation with the donation of Titan Xp GPUs.


  1. 1.
    Daubechies, I.: Ten Lectures on Wavelets, vol. 61. Siam, Philadelphia (1992)CrossRefGoogle Scholar
  2. 2.
    Frazier, M.W.: An Introduction to Wavelets Through Linear Algebra. Springer, Heidelberg (2006)zbMATHGoogle Scholar
  3. 3.
    Fujieda, S., Takayama, K., Hachisuka, T.: Wavelet convolutional neural networks. arXiv preprint arXiv:1805.08620 (2018)
  4. 4.
    Huang, H., He, R., Sun, Z., Tan, T.: Wavelet-SRNet: a wavelet-based CNN for multi-scale face super resolution. In: CVPR, pp. 1689–1697 (2017)Google Scholar
  5. 5.
    Krizhevsky, A., Hinton, G.: Learning multiple layers of features from tiny images. Technical report, Citeseer (2009)Google Scholar
  6. 6.
    LeCun, Y.: The MNIST database of handwritten digits (1998).
  7. 7.
    Netzer, Y., Wang, T., Coates, A., Bissacco, A., Wu, B., Ng, A.Y.: Reading digits in natural images with unsupervised feature learning. In: NIPS Workshop on Deep Learning and Unsupervised Feature Learning, vol. 2011, p. 5 (2011)Google Scholar
  8. 8.
    Williams, T., Li, R.: Wavelet pooling for convolutional neural networks. In: International Conference on Learning Representations (2018).

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Universitat de BarcelonaBarcelonaSpain
  2. 2.Computer Vision CenterBarcelonaSpain

Personalised recommendations