270 citations · 594 across the 17 of their papers we have counts for
6 papers · 1 filter
Affine Self Convolution
Nichita Diaconu, Daniel E Worrall
Attention mechanisms, and most prominently self-attention, are a powerful building block for processing not only text but also images. These provide a parameter efficient method fo…
Reversible GANs for Memory-efficient Image-to-Image Translation
Tycho F. A. van der Ouderaa, Daniel E. Worrall
The Pix2pix and CycleGAN losses have vastly improved the qualitative and quantitative visual quality of results in image-to-image translation tasks. We extend this framework by exp…
CubeNet: Equivariance to 3D Rotation and Translation
Daniel Worrall, Gabriel Brostow
3D Convolutional Neural Networks are sensitive to transformations applied to their input. This is a problem because a voxelized version of a 3D object, and its rotated clone, will…
Interpretable Transformations with Encoder-Decoder Networks
Daniel E. Worrall, Stephan J. Garbin, Daniyar Turmukhambetov +1
Deep feature spaces have the capacity to encode complex transformations of their input data. However, understanding the relative feature-space relationship between two transformed…
Bayesian Image Quality Transfer with CNNs: Exploring Uncertainty in dMRI Super-Resolution
Ryutaro Tanno, Daniel E. Worrall, Aurobrata Ghosh +4
In this work, we investigate the value of uncertainty modeling in 3D super-resolution with convolutional neural networks (CNNs). Deep learning has shown success in a plethora of me…
Harmonic Networks: Deep Translation and Rotation Equivariance
Daniel E. Worrall, Stephan J. Garbin, Daniyar Turmukhambetov +1
Translating or rotating an input image should not affect the results of many computer vision tasks. Convolutional neural networks (CNNs) are already translation equivariant: input…