Saved in:
Bibliographic Details
Main Authors: Zhemchuzhnikov, Dmitrii, Grudinin, Sergei
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2403.19612
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909543822262272
author Zhemchuzhnikov, Dmitrii
Grudinin, Sergei
author_facet Zhemchuzhnikov, Dmitrii
Grudinin, Sergei
contents Effective recognition of spatial patterns and learning their hierarchy is crucial in modern spatial data analysis. Volumetric data applications seek techniques ensuring invariance not only to shifts but also to pattern rotations. While traditional methods can readily achieve translational invariance, rotational invariance possesses multiple challenges and remains an active area of research. Here, we present ILPO-Net (Invariant to Local Patterns Orientation Network), a novel approach that handles arbitrarily shaped patterns with the convolutional operation inherently invariant to local spatial pattern orientations using the Wigner matrix expansions. Our architecture seamlessly integrates the new convolution operator and, when benchmarked on diverse volumetric datasets such as MedMNIST and CATH, demonstrates superior performance over the baselines with significantly reduced parameter counts - up to 1000 times fewer in the case of MedMNIST. Beyond these demonstrations, ILPO-Net's rotational invariance paves the way for other applications across multiple disciplines. Our code is publicly available at https://gricad-gitlab.univ-grenoble-alpes.fr/GruLab/ILPO/-/tree/main/ILPONet.
format Preprint
id arxiv_https___arxiv_org_abs_2403_19612
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ILPO-NET: Network for the invariant recognition of arbitrary volumetric patterns in 3D
Zhemchuzhnikov, Dmitrii
Grudinin, Sergei
Computer Vision and Pattern Recognition
Machine Learning
Effective recognition of spatial patterns and learning their hierarchy is crucial in modern spatial data analysis. Volumetric data applications seek techniques ensuring invariance not only to shifts but also to pattern rotations. While traditional methods can readily achieve translational invariance, rotational invariance possesses multiple challenges and remains an active area of research. Here, we present ILPO-Net (Invariant to Local Patterns Orientation Network), a novel approach that handles arbitrarily shaped patterns with the convolutional operation inherently invariant to local spatial pattern orientations using the Wigner matrix expansions. Our architecture seamlessly integrates the new convolution operator and, when benchmarked on diverse volumetric datasets such as MedMNIST and CATH, demonstrates superior performance over the baselines with significantly reduced parameter counts - up to 1000 times fewer in the case of MedMNIST. Beyond these demonstrations, ILPO-Net's rotational invariance paves the way for other applications across multiple disciplines. Our code is publicly available at https://gricad-gitlab.univ-grenoble-alpes.fr/GruLab/ILPO/-/tree/main/ILPONet.
title ILPO-NET: Network for the invariant recognition of arbitrary volumetric patterns in 3D
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2403.19612