622 citations · 791 across the 7 of their papers we have counts for
7 papers
Magnetorotational instability in a solar near-surface mean-field dynamo
Axel Brandenburg, Gustav Larsson, Fabio Del Sordo +1
We address the question whether the magnetorotational instability (MRI) can operate in the near-surface shear layer (NSSL) of the Sun and how it affects the interaction with the dy…
Turbulence with Magnetic Helicity that is Absent on Average
Axel Brandenburg, Gustav Larsson
Magnetic helicity plays a tremendously important role when it is different from zero on average. Most notably, it leads to the phenomenon of an inverse cascade. Here, we consider d…
Self-Supervised Relative Depth Learning for Urban Scene Understanding
Huaizu Jiang, Erik Learned-Miller, Gustav Larsson +2
As an agent moves through the world, the apparent motion of scene elements is (usually) inversely proportional to their depth. It is natural for a learning agent to associate image…
Discovery of Visual Semantics by Unsupervised and Self-Supervised Representation Learning
Gustav Larsson
The success of deep learning in computer vision is rooted in the ability of deep networks to scale up model complexity as demanded by challenging visual tasks. As complexity is inc…
Colorization as a Proxy Task for Visual Understanding
Gustav Larsson, Michael Maire, Gregory Shakhnarovich
We investigate and improve self-supervision as a drop-in replacement for ImageNet pretraining, focusing on automatic colorization as the proxy task. Self-supervised training has be…
FractalNet: Ultra-Deep Neural Networks without Residuals
Gustav Larsson, Michael Maire, Gregory Shakhnarovich
We introduce a design strategy for neural network macro-architecture based on self-similarity. Repeated application of a simple expansion rule generates deep networks whose structu…
Learning Representations for Automatic Colorization
Gustav Larsson, Michael Maire, Gregory Shakhnarovich
We develop a fully automatic image colorization system. Our approach leverages recent advances in deep networks, exploiting both low-level and semantic representations. As many sce…