ILPO-NET: Network for the invariant recognition of arbitrary volumetric patterns in 3D - Multidisciplinary Institute in Artificial intelligence - Grenoble Alpes Access content directly
Conference Papers Year : 2024

ILPO-NET: Network for the invariant recognition of arbitrary volumetric patterns in 3D

Abstract

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.
Fichier principal
Vignette du fichier
ILPONet_revisions.pdf (8.69 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-04632077 , version 1 (02-07-2024)

Licence

Identifiers

  • HAL Id : hal-04632077 , version 1

Cite

Dmitrii Zhemchuzhnikov, Sergei Grudinin. ILPO-NET: Network for the invariant recognition of arbitrary volumetric patterns in 3D. European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, Sep 2024, Vilnius, Lithuania. ⟨hal-04632077⟩
0 View
0 Download

Share

Gmail Mastodon Facebook X LinkedIn More