.png){kind=icon}
.png){kind=icon}
Return
Circular-symmetric correlation layer
.png){kind=icon}
OA
AI
DOI：10.1007/s10994-022-06288-4.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
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 x 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.
Keywords:
Equivariant neural networks
Panoramic image processing
LiDAR segmentation
Fast Fourier transform (FFT)