1 code implementation • 9 Apr 2024 • Enrique Fita Sanmartín, Christoph Schnörr, Fred A. Hamprecht
Spanning trees are an important primitive in many data analysis tasks, when a data set needs to be summarized in terms of its "skeleton", or when a tree-shaped graph over all observations is required for downstream processing.
no code implementations • 12 Feb 2024 • Bastian Boll, Daniel Gonzalez-Alvarado, Christoph Schnörr
This paper introduces a novel generative model for discrete distributions based on continuous normalizing flows on the submanifold of factorizing discrete measures.
no code implementations • 9 Feb 2024 • Felix Draxler, Stefan Wahl, Christoph Schnörr, Ullrich Köthe
We present a novel theoretical framework for understanding the expressive power of coupling-based normalizing flows such as RealNVP.
no code implementations • 30 Jun 2023 • Jonathan Schwarz, Jonas Cassel, Bastian Boll, Martin Gärttner, Peter Albers, Christoph Schnörr
This paper introduces assignment flows for density matrices as state spaces for representing and analyzing data associated with vertices of an underlying weighted graph.
1 code implementation • 23 Jun 2023 • Felix Draxler, Lars Kühmichel, Armand Rousselot, Jens Müller, Christoph Schnörr, Ullrich Köthe
Gaussianization is a simple generative model that can be trained without backpropagation.
2 code implementations • 25 Oct 2022 • Felix Draxler, Christoph Schnörr, Ullrich Köthe
For the first time, we make a quantitative statement about this kind of convergence: We prove that all coupling-based normalizing flows perform whitening of the data distribution (i. e. diagonalize the covariance matrix) and derive corresponding convergence bounds that show a linear convergence rate in the depth of the flow.
no code implementations • 9 May 2022 • Dmitrij Sitenko, Bastian Boll, Christoph Schnörr
We devise an entropy-regularized difference-of-convex-functions (DC) decomposition of this potential and show that the basic geometric Euler scheme for integrating the assignment flow is equivalent to solving the G-PDE by an established DC programming scheme.
1 code implementation • 26 Jan 2022 • Bastian Boll, Alexander Zeilmann, Stefania Petra, Christoph Schnörr
We propose a novel class of deep stochastic predictors for classifying metric data on graphs within the PAC-Bayes risk certification paradigm.
no code implementations • 21 Jan 2022 • Christian Homeyer, Oliver Lange, Christoph Schnörr
3D reconstruction of depth and motion from monocular video in dynamic environments is a highly ill-posed problem due to scale ambiguities when projecting to the 2D image domain.
no code implementations • 19 Aug 2021 • David Schnörr, Christoph Schnörr
The Turing mechanism describes the emergence of spatial patterns due to spontaneous symmetry breaking in reaction-diffusion processes and underlies many developmental processes.
no code implementations • 2 Aug 2021 • Alexander Zeilmann, Stefania Petra, Christoph Schnörr
An exact formula is derived for the parameter gradient of any loss function that is constrained by the linear system of ODEs determining the linearized assignment flow.
no code implementations • 26 Feb 2020 • Artjom Zern, Alexander Zeilmann, Christoph Schnörr
The assignment flow recently introduced in the J.
no code implementations • 8 Nov 2019 • Matthias Zisler, Artjom Zern, Stefania Petra, Christoph Schnörr
This paper extends the recently introduced assignment flow approach for supervised image labeling to unsupervised scenarios where no labels are given.
no code implementations • 22 Oct 2019 • Ruben Hühnerbein, Fabrizio Savarino, Stefania Petra, Christoph Schnörr
We study the inverse problem of model parameter learning for pixelwise image labeling, using the linear assignment flow and training data with ground truth.
1 code implementation • 11 Jun 2019 • Nikolaos Gianniotis, Christoph Schnörr, Christian Molkenthin, Sanjay Singh Bora
Variational methods are employed in situations where exact Bayesian inference becomes intractable due to the difficulty in performing certain integrals.
no code implementations • 24 Apr 2019 • Artjom Zern, Matthias Zisler, Stefania Petra, Christoph Schnörr
Experiments demonstrate a beneficial effect in both directions: adaptivity of labels improves image labeling, and steering label evolution by spatially regularized assignments leads to proper labels, because the assignment flow for supervised labeling is exactly used without any approximation for label learning.
no code implementations • 4 Oct 2017 • Ruben Hühnerbein, Fabrizio Savarino, Freddie Åström, Christoph Schnörr
We introduce a novel approach to Maximum A Posteriori inference based on discrete graphical models.
1 code implementation • 21 Aug 2017 • Mattia Desana, Christoph Schnörr
SPGMs combine traits from Sum-Product Networks (SPNs) and Graphical Models (GMs): Like SPNs, SPGMs always enable tractable inference using a class of models that incorporate context specific independence.
no code implementations • 25 Jul 2016 • Francesco Silvestri, Gerhard Reinelt, Christoph Schnörr
We consider clustering problems where the goal is to determine an optimal partition of a given point set in Euclidean space in terms of a collection of affine subspaces.
no code implementations • 7 Jun 2016 • Johannes Berger, Christoph Schnörr
Monocular scene reconstruction is essential for modern applications such as robotics or autonomous driving.
no code implementations • 19 May 2016 • Freddie Åström, Christoph Schnörr
Our energy is a non-convex, non-smooth higher-order vectorial total variation approach and promotes color consistent image filtering via a coupling term.
no code implementations • 25 Apr 2016 • Mattia Desana, Christoph Schnörr
Sum-Product Networks with complex probability distribution at the leaves have been shown to be powerful tractable-inference probabilistic models.
no code implementations • 16 Mar 2016 • Freddie Åström, Stefania Petra, Bernhard Schmitzer, Christoph Schnörr
We introduce a novel geometric approach to the image labeling problem.
no code implementations • 9 Jan 2016 • Jörg Hendrik Kappes, Paul Swoboda, Bogdan Savchynskyy, Tamir Hazan, Christoph Schnörr
We present a probabilistic graphical model formulation for the graph clustering problem.
no code implementations • CVPR 2014 • Paul Swoboda, Alexander Shekhovtsov, Jörg Hendrik Kappes, Christoph Schnörr, Bogdan Savchynskyy
We propose a novel polynomial time algorithm to obtain a part of its optimal non-relaxed integral solution.
no code implementations • 15 Jul 2014 • Bernhard Schmitzer, Christoph Schnörr
While the overall functional is non-convex, non-convexity is confined to a low-dimensional variable.
no code implementations • 3 Jul 2014 • Frank Lenzen, Jan Lellmann, Florian Becker, Christoph Schnörr
In the present paper we prove uniqueness for a larger class of problems and in particular independent of the image size.
no code implementations • 2 Apr 2014 • Jörg H. Kappes, Bjoern Andres, Fred A. Hamprecht, Christoph Schnörr, Sebastian Nowozin, Dhruv Batra, Sungwoong Kim, Bernhard X. Kausler, Thorben Kröger, Jan Lellmann, Nikos Komodakis, Bogdan Savchynskyy, Carsten Rother
However, on new and challenging types of models our findings disagree and suggest that polyhedral methods and integer programming solvers are competitive in terms of runtime and solution quality over a large range of model types.
no code implementations • 31 Mar 2014 • Fabian Rathke, Stefan Schmidt, Christoph Schnörr
With the introduction of spectral-domain optical coherence tomography (OCT), resulting in a significant increase in acquisition speed, the fast and accurate segmentation of 3-D OCT scans has become evermore important.
no code implementations • NeurIPS 2013 • Bogdan Savchynskyy, Jörg Hendrik Kappes, Paul Swoboda, Christoph Schnörr
We consider energy minimization for undirected graphical models, also known as MAP-inference problem for Markov random fields.
no code implementations • 28 Nov 2013 • Eva-Maria Didden, Thordis Linda Thorarinsdottir, Alex Lenkoski, Christoph Schnörr
Shape from texture refers to the extraction of 3D information from 2D images with irregular texture.
no code implementations • 9 Sep 2013 • Bernhard Schmitzer, Christoph Schnörr
Describing shapes by suitable measures in object segmentation, as proposed in [24], allows to combine the advantages of the representations as parametrized contours and indicator functions.
no code implementations • 16 Jan 2013 • Paul Swoboda, Christoph Schnörr
We present a novel variational approach to image restoration (e. g., denoising, inpainting, labeling) that enables to complement established variational approaches with a histogram-based prior enforcing closeness of the solution to some given empirical measure.