598 citations · 2.9k across the 89 of their papers we have counts for
18 papers · 1 filter
Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networks
Agustinus Kristiadi, Matthias Hein, Philipp Hennig
The point estimates of ReLU classification networks---arguably the most widely used neural network architecture---have been shown to yield arbitrarily high confidence far away from…
The Power Mean Laplacian for Multilayer Graph Clustering
Pedro Mercado, Antoine Gautier, Francesco Tudisco +1
Multilayer graphs encode different kind of interactions between the same set of entities. When one wants to cluster such a multilayer graph, the natural question arises how one sho…
Error estimates for spectral convergence of the graph Laplacian on random geometric graphs towards the Laplace--Beltrami operator
Nicolas Garcia Trillos, Moritz Gerlach, Matthias Hein +1
We study the convergence of the graph Laplacian of a random geometric graph generated by an i.i.d. sample from a -dimensional submanifold in as the sample size inc…
Clustering Signed Networks with the Geometric Mean of Laplacians
Pedro Mercado, Francesco Tudisco, Matthias Hein
Signed networks allow to model positive and negative relationships. We analyze existing extensions of spectral clustering to signed networks. It turns out that existing approaches…
Loss Functions for Top-k Error: Analysis and Insights
Maksim Lapin, Matthias Hein, Bernt Schiele
In order to push the performance on realistic computer vision tasks, the number of classes in modern benchmark datasets has significantly increased in recent years. This increase i…
Top-k Multiclass SVM
Maksim Lapin, Matthias Hein, Bernt Schiele
Class ambiguity is typical in image classification problems with a large number of classes. When classes are difficult to discriminate, it makes sense to allow k guesses and evalua…