activity
20172022
most citedDeep Scale-spaces: Equivariance Over Scale

44 citations · 84 across the 7 of their papers we have counts for

collaborators
Showing cs.LGShow all

6 papers · 1 filter

cs.LG20229 cited

Lie Point Symmetry Data Augmentation for Neural PDE Solvers

Johannes Brandstetter, Max Welling, Daniel E. Worrall

Neural networks are increasingly being used to solve partial differential equations (PDEs), replacing slower numerical solvers. However, a critical issue is that neural PDE solvers…

cs.LG2020

MDP Homomorphic Networks: Group Symmetries in Reinforcement Learning

Elise van der Pol, Daniel E. Worrall, Herke van Hoof +2

This paper introduces MDP homomorphic networks for deep reinforcement learning. MDP homomorphic networks are neural networks that are equivariant under symmetries in the joint stat…

cs.LG2020

SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networks

Fabian B. Fuchs, Daniel E. Worrall, Volker Fischer +1

We introduce the SE(3)-Transformer, a variant of the self-attention module for 3D point clouds and graphs, which is equivariant under continuous 3D roto-translations. Equivariance…

cs.LG201944 cited

Deep Scale-spaces: Equivariance Over Scale

Daniel E. Worrall, Max Welling

We introduce deep scale-spaces (DSS), a generalization of convolutional neural networks, exploiting the scale symmetry structure of conventional image recognition tasks. Put plainl…

cs.LG20195 cited

Learning to Convolve: A Generalized Weight-Tying Approach

Nichita Diaconu, Daniel E Worrall

Recent work (Cohen & Welling, 2016) has shown that generalizations of convolutions, based on group theory, provide powerful inductive biases for learning. In these generalizations,…

cs.LG20174 cited

Virtual Adversarial Ladder Networks For Semi-supervised Learning

Saki Shinoda, Daniel E. Worrall, Gabriel J. Brostow

Semi-supervised learning (SSL) partially circumvents the high cost of labeling data by augmenting a small labeled dataset with a large and relatively cheap unlabeled dataset drawn…