Next Article in Journal
Intermittency in Transitional Shear Flows
Previous Article in Journal
The Natural Philosophy of Economic Information: Autonomous Agents and Physiosemiosis
Previous Article in Special Issue
On the Use of Concentrated Time–Frequency Representations as Input to a Deep Convolutional Neural Network: Application to Non Intrusive Load Monitoring
Article

A New Pooling Approach Based on Zeckendorf’s Theorem for Texture Transfer Information

1
Computer Science Department, Univ Evry, Université Paris-Saclay, 91190 Saint-Aubin, France
2
School of Applied Sciences (FCA/UNICAMP), Limeira, Sao Paolo 13484-350, Brazil
3
Computer Sciences Department, Institute of Business Administration, Karachi, Sindh 75270, Pakistan
*
Author to whom correspondence should be addressed.
Academic Editor: Jerry D. Gibsone
Entropy 2021, 23(3), 279; https://doi.org/10.3390/e23030279
Received: 12 December 2020 / Revised: 12 February 2021 / Accepted: 21 February 2021 / Published: 25 February 2021
(This article belongs to the Special Issue Information Transfer in Multilayer/Deep Architectures)
The pooling layer is at the heart of every convolutional neural network (CNN) contributing to the invariance of data variation. This paper proposes a pooling method based on Zeckendorf’s number series. The maximum pooling layers are replaced with Z pooling layer, which capture texels from input images, convolution layers, etc. It is shown that Z pooling properties are better adapted to segmentation tasks than other pooling functions. The method was evaluated on a traditional image segmentation task and on a dense labeling task carried out with a series of deep learning architectures in which the usual maximum pooling layers were altered to use the proposed pooling mechanism. Not only does it arbitrarily increase the receptive field in a parameterless fashion but it can better tolerate rotations since the pooling layers are independent of the geometric arrangement or sizes of the image regions. Different combinations of pooling operations produce images capable of emphasizing low/high frequencies, extract ultrametric contours, etc. View Full-Text
Keywords: deep learning; pooling function; Zeckendorf theorem; Fibonacci; LBP; image representation; segmentation; glioblastoma deep learning; pooling function; Zeckendorf theorem; Fibonacci; LBP; image representation; segmentation; glioblastoma
Show Figures

Figure 1

MDPI and ACS Style

Vigneron, V.; Maaref, H.; Syed, T.Q. A New Pooling Approach Based on Zeckendorf’s Theorem for Texture Transfer Information. Entropy 2021, 23, 279. https://doi.org/10.3390/e23030279

AMA Style

Vigneron V, Maaref H, Syed TQ. A New Pooling Approach Based on Zeckendorf’s Theorem for Texture Transfer Information. Entropy. 2021; 23(3):279. https://doi.org/10.3390/e23030279

Chicago/Turabian Style

Vigneron, Vincent, Hichem Maaref, and Tahir Q. Syed. 2021. "A New Pooling Approach Based on Zeckendorf’s Theorem for Texture Transfer Information" Entropy 23, no. 3: 279. https://doi.org/10.3390/e23030279

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop