• English
  • Deutsch
  • Log In
    Password Login
    or
  • Research Outputs
  • Projects
  • Researchers
  • Institutes
  • Statistics
Repository logo
Fraunhofer-Gesellschaft
  1. Home
  2. Fraunhofer-Gesellschaft
  3. Konferenzschrift
  4. Adaptive wavelet pooling for convolutional neural networks
 
  • Details
  • Full
Options
2021
Conference Paper
Titel

Adaptive wavelet pooling for convolutional neural networks

Abstract
Convolutional neural networks (CNN)s have become the go-to choice for most image and video processing tasks. Most CNN architectures rely on pooling layers to reduce the resolution along spatial dimensions. The reduction allows subsequent deep convolution layers to operate with greater efficiency. This paper introduces adaptive wavelet pooling layers, which employ fast wavelet trans-forms (FWT) to reduce the feature resolution. The FWT decomposes the input features into multiple scales reducing the feature dimensions by removing the fine-scale subbands. Our approach adds extra flexibility through wavelet-basis function optimization and coefficient weighting at different scales. The adaptive wavelet layers integrate directly into well-known CNNs like the LeNet, Alexnet, or Dense net architectures. Using these networks, we validate our approach and find competitive performance on the MNIST, CIFAR-10, and SVHN (streetview house numbers) data-sets.
Author(s)
Wolter, Moritz
Fraunhofer-Institut für Algorithmen und Wissenschaftliches Rechnen SCAI
Garcke, Jochen
Fraunhofer-Institut für Algorithmen und Wissenschaftliches Rechnen SCAI
Hauptwerk
24th International Conference on Artificial Intelligence and Statistics, AISTATS 2021. Proceedings
Konferenz
International Conference on Artificial Intelligence and Statistics (AISTATS) 2021
Thumbnail Image
Externer Link
Externer Link
Language
English
google-scholar
Fraunhofer-Institut für Algorithmen und Wissenschaftliches Rechnen SCAI
  • Cookie settings
  • Imprint
  • Privacy policy
  • Api
  • Send Feedback
© 2022