297 citations · 1.5k across the 199 of their papers we have counts for
9 papers · 1 filter
Accelerating Variance-Reduced Stochastic Gradient Methods
Derek Driggs, Matthias J. Ehrhardt, Carola-Bibiane Schönlieb
Variance reduction is a crucial tool for improving the slow convergence of stochastic gradient descent. Only a few variance-reduced methods, however, have yet been shown to directl…
Dynamic Spectral Residual Superpixels
Jianchao Zhang, Angelica I. Aviles-Rivero, Daniel Heydecker +3
We consider the problem of segmenting an image into superpixels in the context of -means clustering, in which we wish to decompose an image into local, homogeneous regions corre…
PDE-Inspired Algorithms for Semi-Supervised Learning on Point Clouds
Oliver M. Crook, Tim Hurst, Carola-Bibiane Schönlieb +2
Given a data set and a subset of labels the problem of semi-supervised learning on point clouds is to extend the labels to the entire data set. In this paper we extend the labels b…
Energy Models for Better Pseudo-Labels: Improving Semi-Supervised Classification with the 1-Laplacian Graph Energy
Angelica I. Aviles-Rivero, Nicolas Papadakis, Ruoteng Li +4
Semi-supervised classification is a great focus of interest, as in real-world scenarios obtaining labels is expensive, time-consuming and might require expert knowledge. This has m…
A hybrid analytical-numerical algorithm for determining the neuronal current via EEG
Parham Hashemzadeh, A. S. Fokas, C. B. Schönlieb
In this study, the neuronal current in the brain is represented using Helmholtz decomposition. It was shown in earlier work that data obtained via electroencephalography (EEG) are…
On the Connection Between Adversarial Robustness and Saliency Map Interpretability
Christian Etmann, Sebastian Lunz, Peter Maass +1
Recent studies on the adversarial vulnerability of neural networks have shown that models trained to be more robust to adversarial attacks exhibit more interpretable saliency maps…
Learning optimal orders of the underlying Euclidean norm in total variation image denoising
Pan Liu, Carola-Bibiane Schönlieb
A novel class of semi-norms, generalising the notion of the isotropic total variation and the an-isotropic total variation is introduced. A supervised learning me…
A total variation based regularizer promoting piecewise-Lipschitz reconstructions
Martin Burger, Yury Korolev, Carola-Bibiane Schönlieb +1
We introduce a new regularizer in the total variation family that promotes reconstructions with a given Lipschitz constant (which can also vary spatially). We prove regularizing pr…
Multi-tasking to Correct: Motion-Compensated MRI via Joint Reconstruction and Registration
Veronica Corona, Angelica I. Aviles-Rivero, Noemie Debroux +4
This work addresses a central topic in Magnetic Resonance Imaging (MRI) which is the motion-correction problem in a joint reconstruction and registration framework. From a set of m…