Maurice Weiler
Maurice Weiler
Home
PhD-Thesis
Blog
Publications
CV
1
A Program to build E(N)-Equivariant Steerable CNNs
Equivariance is becoming an increasingly popular design choice to build data efficient neural networks by exploiting prior knowledge …
Gabriele Cesa
,
Leon Lang
,
Maurice Weiler
arXiv
PDF
Code
Cite
Steerable Partial Differential Operators for Equivariant Neural Networks
Recent work in equivariant deep learning bears strong similarities to physics. Fields over a base space are fundamental entities in …
Erik Jenner
,
Maurice Weiler
arXiv
PDF
Code
Cite
A Wigner-Eckart Theorem for Group Equivariant Convolution Kernels
Group equivariant convolutional networks (GCNNs) endow classical convolutional networks with additional symmetry priors, which can lead …
Leon Lang
,
Maurice Weiler
arXiv
PDF
Cite
Gauge Equivariant Mesh CNNs
A common approach to define convolutions on meshes is to interpret them as a graph and apply graph convolutional networks (GCNs). Such …
Pim de Haan
,
Maurice Weiler
,
Taco Cohen
,
Max Welling
arXiv
PDF
Code
Cite
General E(2)-Equivariant Steerable CNNs
The big empirical success of group equivariant networks has led in recent years to the sprouting of a great variety of equivariant …
Maurice Weiler
,
Gabriele Cesa
arXiv
PDF
Code
Cite
Gauge Equivariant Convolutional Networks and the Icosahedral CNN
The principle of equivariance to symmetry transformations enables a theoretically grounded approach to neural network architecture …
Taco Cohen
,
Maurice Weiler
,
Berkay Kicanaoglu
,
Max Welling
arXiv
PDF
Cite
A General Theory of Equivariant CNNs on Homogeneous Spaces
We present a general theory of Group equivariant Convolutional Neural Networks (G-CNNs) on homogeneous spaces such as Euclidean space …
Taco Cohen
,
Mario Geiger
,
Maurice Weiler
arXiv
PDF
Cite
3D Steerable CNNs
We present a convolutional network that is equivariant to rigid body motions. The model uses scalar-, vector-, and tensor fields over …
Maurice Weiler
,
Mario Geiger
,
Max Welling
,
Wouter Boomsma
,
Taco Cohen
arXiv
PDF
Code
Cite
Learning Steerable Filters for Rotation Equivariant CNNs
In many machine learning tasks it is desirable that a model’s prediction transforms in an equivariant way under transformations …
Maurice Weiler
,
Fred A. Hamprecht
,
Martin Storath
arXiv
PDF
Cite
Cite
×