ILPO-NET: Network for the invariant recognition of arbitrary volumetric patterns in 3D
This addresses the challenge of rotational invariance in spatial data analysis for applications like medical imaging and structural biology, representing a novel method rather than an incremental improvement.
The paper tackles the problem of achieving rotational invariance in 3D volumetric pattern recognition, presenting ILPO-Net, which uses Wigner matrix expansions to handle arbitrarily shaped patterns and demonstrates superior performance with up to 1000 times fewer parameters on datasets like MedMNIST and CATH.
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.