Hartley Spectral Pooling for Deep Learning

10/07/2018
by   Hao Zhang, et al.
0

In most convolution neural networks (CNNs), downsampling hidden layers is adopted for increasing computation efficiency and the receptive field size. Such operation is commonly so-called pooling. Maximation and averaging over sliding windows (max/average pooling), and plain downsampling in the form of strided convolution are popular pooling methods. Since the pooling is a lossy procedure, a motivation of our work is to design a new pooling approach for less lossy in the dimensionality reduction. Inspired by the Fourier spectral pooling(FSP) proposed by Rippel et. al. [1], we present the Hartley transform based spectral pooling method in CNNs. Compared with FSP, the proposed spectral pooling avoids the use of complex arithmetic for frequency representation and reduces the computation. Spectral pooling preserves more structure features for network's discriminability than max and average pooling. We empirically show that Hartley spectral pooling gives rise to the convergence of training CNNs on MNIST and CIFAR-10 datasets.

READ FULL TEXT
research
06/11/2015

Spectral Representations for Convolutional Neural Networks

Discrete Fourier transforms provide a significant speedup in the computa...
research
04/11/2018

Detail-Preserving Pooling in Deep Networks

Most convolutional neural networks use some method for gradually downsca...
research
06/10/2019

A Closed-Form Learned Pooling for Deep Classification Networks

In modern computer vision tasks, convolutional neural networks (CNNs) ar...
research
06/10/2016

Deep CNNs along the Time Axis with Intermap Pooling for Robustness to Spectral Variations

Convolutional neural networks (CNNs) with convolutional and pooling oper...
research
06/30/2012

Differentiable Pooling for Hierarchical Feature Learning

We introduce a parametric form of pooling, based on a Gaussian, which ca...
research
08/12/2019

LIP: Local Importance-based Pooling

Spatial downsampling layers are favored in convolutional neural networks...
research
11/25/2022

MorphPool: Efficient Non-linear Pooling Unpooling in CNNs

Pooling is essentially an operation from the field of Mathematical Morph...

Please sign up or login with your details

Forgot password? Click here to reset