Analysis of (sub-)Riemannian PDE-G-CNNs
Group equivariant convolutional neural networks (G-CNNs) have been successfully applied in geometric deep learning. Typically, G-CNNs have the advantage over CNNs that they do not waste network capacity on training symmetries that should have been hard-coded in the network. The recently introduced f...
Gespeichert in:
Hauptverfasser: | , , , , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | Group equivariant convolutional neural networks (G-CNNs) have been
successfully applied in geometric deep learning. Typically, G-CNNs have the
advantage over CNNs that they do not waste network capacity on training
symmetries that should have been hard-coded in the network. The recently
introduced framework of PDE-based G-CNNs (PDE-G-CNNs) generalises G-CNNs.
PDE-G-CNNs have the core advantages that they simultaneously 1) reduce network
complexity, 2) increase classification performance, and 3) provide geometric
interpretability. Their implementations primarily consist of linear and
morphological convolutions with kernels.
In this paper we show that the previously suggested approximative
morphological kernels do not always accurately approximate the exact kernels
accurately. More specifically, depending on the spatial anisotropy of the
Riemannian metric, we argue that one must resort to sub-Riemannian
approximations. We solve this problem by providing a new approximative kernel
that works regardless of the anisotropy. We provide new theorems with better
error estimates of the approximative kernels, and prove that they all carry the
same reflectional symmetries as the exact ones.
We test the effectiveness of multiple approximative kernels within the
PDE-G-CNN framework on two datasets, and observe an improvement with the new
approximative kernels. We report that the PDE-G-CNNs again allow for a
considerable reduction of network complexity while having comparable or better
performance than G-CNNs and CNNs on the two datasets. Moreover, PDE-G-CNNs have
the advantage of better geometric interpretability over G-CNNs, as the
morphological kernels are related to association fields from neurogeometry. |
---|---|
DOI: | 10.48550/arxiv.2210.00935 |