What is it about?
The need to detect and classify objects correctly is a constant challenge, being able to recognize them at different scales and scenarios, sometimes cropped or badly lit is not an easy task. Convolutional neural networks (CNN) have become a widely applied technique since they are completely trainable and suitable to extract features. Here, we propose a hybrid pooling method that incorporates multiresolution analysis within the CNN layers to reduce the feature map size without losing details.
Featured Image
Photo by Clint Adair on Unsplash
Why is it important?
We propose a hybrid pooling method that incorporates multiresolution analysis within the CNN layers to reduce the feature map size without losing details. To prevent relevant information from losing during the downsampling process an existing pooling method is combined with the wavelet transform technique, keeping those details "alive" and enriching other stages of the CNN.
Perspectives
Read the Original
This page is a summary of: Hybrid pooling with wavelets for convolutional neural networks, Journal of Intelligent & Fuzzy Systems, March 2022, IOS Press,
DOI: 10.3233/jifs-219223.
You can read the full text:
Contributors
The following have contributed to this page