Skip to Main content Skip to Navigation
Journal articles

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

Abstract : 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.
Document type :
Journal articles
Complete list of metadata
Contributor : Frédéric Davesne Connect in order to contact the contributor
Submitted on : Sunday, March 21, 2021 - 5:20:47 PM
Last modification on : Friday, August 5, 2022 - 11:41:04 AM

Links full text



Vincent Vigneron, Hichem Maaref, Tahir Syed. A New Pooling Approach Based on Zeckendorf’s Theorem for Texture Transfer Information. Entropy, MDPI, 2021, 23 (3), pp.279. ⟨10.3390/e23030279⟩. ⟨hal-03175879⟩



Record views