Search Results for author:
Found 12 papers, 7 papers with code
Neural Simulated Annealing
Simulated annealing (SA) is a stochastic global optimisation technique applicable to a wide range of discrete and continuous variable problems.
Lie Point Symmetry Data Augmentation for Neural PDE Solvers
In this paper, we present a method, which can partially alleviate this problem, by improving neural PDE solver sample complexity -- Lie point symmetry data augmentation (LPSDA).
MDP Homomorphic Networks: Group Symmetries in Reinforcement Learning
MDP homomorphic networks are neural networks that are equivariant under symmetries in the joint state-action space of an MDP.
SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networks
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.
Affine Self Convolution
We also modify the Squeeze and Excitation variant of attention, extending both variants of attention to the roto-translation group.
Deep Scale-spaces: Equivariance Over Scale
We introduce deep scale-spaces (DSS), a generalization of convolutional neural networks, exploiting the scale symmetry structure of conventional image recognition tasks.
Learning to Convolve: A Generalized Weight-Tying Approach
In this paper, we learn how to transform filters for use in the group convolution, focussing on roto-translation.
Reversible GANs for Memory-efficient Image-to-Image Translation
The Pix2pix and CycleGAN losses have vastly improved the qualitative and quantitative visual quality of results in image-to-image translation tasks.
Virtual Adversarial Ladder Networks For Semi-supervised Learning
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 from the same distribution.
Interpretable Transformations with Encoder-Decoder Networks
We propose a simple method to construct a deep feature space, with explicitly disentangled representations of several known transformations.
Bayesian Image Quality Transfer with CNNs: Exploring Uncertainty in dMRI Super-Resolution
In this work, we investigate the value of uncertainty modeling in 3D super-resolution with convolutional neural networks (CNNs).
