返回
Circular-symmetric correlation layer
DOI:10.1007/s10994-022-06288-4.png)
摘要
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.
Keyword:
Equivariant neural networks
Panoramic image processing
LiDAR segmentation
Fast Fourier transform (FFT)
期刊
IF:
2.9
论文数:
2.7K
被引数:
3.4W
机构
引用论文
More tricks with tetramers: a practical guide to staining T cells with peptide–MHC multimers
Immunology
IF0
Comparative study of layer by layer assembled multilayer films based on graphene oxide and reduced graphene oxide on flexible polyurethane foam: flame retardant and smoke suppression properties
RSC Advances
IF0
Pressure-Based Bioassay Perceived by a Flexible Pressure Sensor with Synergistic Enhancement of the Photothermal Effect通过具有协同增强光热效应的柔性压力传感器感知的基于压力的生物测定
Computerized techniques pave the way for drug-drug interaction prediction and interpretation
BioImpacts
IF0
Sub-equilibrium oxygen-18 and carbon-13 levels in biological carbonates: carbonate and kinetic models
Coral Reefs
IF0

