Saved in:
Bibliographic Details
Main Authors: Rahman, Md Ashiqur, Yeh, Raymond A.
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2504.17258
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908335930867712
author Rahman, Md Ashiqur
Yeh, Raymond A.
author_facet Rahman, Md Ashiqur
Yeh, Raymond A.
contents Downsampling layers are crucial building blocks in CNN architectures, which help to increase the receptive field for learning high-level features and reduce the amount of memory/computation in the model. In this work, we study the generalization of the uniform downsampling layer for group equivariant architectures, e.g., G-CNNs. That is, we aim to downsample signals (feature maps) on general finite groups with anti-aliasing. This involves the following: (a) Given a finite group and a downsampling rate, we present an algorithm to form a suitable choice of subgroup. (b) Given a group and a subgroup, we study the notion of bandlimited-ness and propose how to perform anti-aliasing. Notably, our method generalizes the notion of downsampling based on classical sampling theory. When the signal is on a cyclic group, i.e., periodic, our method recovers the standard downsampling of an ideal low-pass filter followed by a subsampling operation. Finally, we conducted experiments on image classification tasks demonstrating that the proposed downsampling operation improves accuracy, better preserves equivariance, and reduces model size when incorporated into G-equivariant networks
format Preprint
id arxiv_https___arxiv_org_abs_2504_17258
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Group Downsampling with Equivariant Anti-aliasing
Rahman, Md Ashiqur
Yeh, Raymond A.
Machine Learning
Computer Vision and Pattern Recognition
Group Theory
Downsampling layers are crucial building blocks in CNN architectures, which help to increase the receptive field for learning high-level features and reduce the amount of memory/computation in the model. In this work, we study the generalization of the uniform downsampling layer for group equivariant architectures, e.g., G-CNNs. That is, we aim to downsample signals (feature maps) on general finite groups with anti-aliasing. This involves the following: (a) Given a finite group and a downsampling rate, we present an algorithm to form a suitable choice of subgroup. (b) Given a group and a subgroup, we study the notion of bandlimited-ness and propose how to perform anti-aliasing. Notably, our method generalizes the notion of downsampling based on classical sampling theory. When the signal is on a cyclic group, i.e., periodic, our method recovers the standard downsampling of an ideal low-pass filter followed by a subsampling operation. Finally, we conducted experiments on image classification tasks demonstrating that the proposed downsampling operation improves accuracy, better preserves equivariance, and reduces model size when incorporated into G-equivariant networks
title Group Downsampling with Equivariant Anti-aliasing
topic Machine Learning
Computer Vision and Pattern Recognition
Group Theory
url https://arxiv.org/abs/2504.17258