Circular-Symmetric Correlation Layer based on FFT

07/26/2021
by   Bahar Azari, et al.
0

Despite the vast success of standard planar convolutional neural networks, they are not the most efficient choice for analyzing signals that lie on an arbitrarily curved manifold, such as a cylinder. The problem arises when one performs a planar projection of these signals and inevitably causes them to be distorted or broken where there is valuable information. We propose a Circular-symmetric Correlation Layer (CCL) based on the formalism of roto-translation equivariant correlation on the continuous group S^1 ×ℝ, and implement it efficiently using the well-known Fast Fourier Transform (FFT) algorithm. We showcase the performance analysis of a general network equipped with CCL on various recognition and classification tasks and datasets. The PyTorch package implementation of CCL is provided online.

READ FULL TEXT

page 6

page 9

research
06/18/2020

Conformal Moduli of Symmetric Circular Quadrilaterals With Cusps

We investigate moduli of planar circular quadrilaterals symmetric with r...
research
01/30/2018

Spherical CNNs

Convolutional Neural Networks (CNNs) have become the method of choice fo...
research
01/25/2016

Very Efficient Training of Convolutional Neural Networks using Fast Fourier Transform and Overlap-and-Add

Convolutional neural networks (CNNs) are currently state-of-the-art for ...
research
10/29/2018

Phase Harmonics and Correlation Invariants in Convolutional Neural Networks

We prove that linear rectifiers act as phase transformations on complex ...
research
03/03/2022

Fully-Connected Network on Noncompact Symmetric Space and Ridgelet Transform based on Helgason-Fourier Analysis

Neural network on Riemannian symmetric space such as hyperbolic space an...
research
04/08/2019

Non-commutative Rényi Entropic Uncertainty Principles

In this paper, we calculate the norm of the string Fourier transform on ...
research
11/10/2014

Zero-Aliasing Correlation Filters for Object Recognition

Correlation filters (CFs) are a class of classifiers that are attractive...

Please sign up or login with your details

Forgot password? Click here to reset