84 citations · 213 across the 28 of their papers we have counts for
32 papers
Compute Time Scaling with Recursive Models for Combinatorial Optimization
Zhengxi Zhang, Paul Swoboda
We propose Tiny Recursive Models for Combinatorial Optimization (\ours{}), a general neural method for combinatorial optimization that scales both depth (how often we recursively i…
DiscoMatch: Fast Discrete Optimisation for Geometrically Consistent 3D Shape Matching
Paul Roetzer, Ahmed Abbas, Dongliang Cao +2
In this work we propose to combine the advantages of learningbased and combinatorial formalisms for 3D shape matching. While learningbased methods lead to state-of-the-art matching…
A Multidimensional Analysis of Social Biases in Vision Transformers
Jannik Brinkmann, Paul Swoboda, Christian Bartelt
The embedding spaces of image models have been shown to encode a range of social biases such as racism and sexism. Here, we investigate specific factors that contribute to the emer…
LVM-Med: Learning Large-Scale Self-Supervised Vision Models for Medical Imaging via Second-order Graph Matching
Duy M. H. Nguyen, Hoang Nguyen, Nghiem T. Diep +9
Obtaining large pre-trained models that can be fine-tuned to new tasks with limited annotated samples has remained an open challenge for medical imaging data. While pre-trained dee…
ClusterFuG: Clustering Fully connected Graphs by Multicut
Ahmed Abbas, Paul Swoboda
We propose a graph clustering formulation based on multicut (a.k.a. weighted correlation clustering) on the complete graph. Our formulation does not need specification of the graph…
Joint Self-Supervised Image-Volume Representation Learning with Intra-Inter Contrastive Clustering
Duy M. H. Nguyen, Hoang Nguyen, Mai T. N. Truong +7
Collecting large-scale medical datasets with fully annotated samples for training of deep networks is prohibitively expensive, especially for 3D volume data. Recent breakthroughs i…
A Comparative Study of Graph Matching Algorithms in Computer Vision
Stefan Haller, Lorenz Feineis, Lisa Hutschenreiter +5
The graph matching optimization problem is an essential component for many tasks in computer vision, such as bringing two deformable objects in correspondence. Naturally, a wide ra…
DOGE-Train: Discrete Optimization on GPU with End-to-end Training
Ahmed Abbas, Paul Swoboda
We present a fast, scalable, data-driven approach for solving relaxations of 0-1 integer linear programs. We use a combination of graph neural networks (GNN) and the Lagrange decom…
A Scalable Combinatorial Solver for Elastic Geometrically Consistent 3D Shape Matching
Paul Roetzer, Paul Swoboda, Daniel Cremers +1
We present a scalable combinatorial algorithm for globally optimizing over the space of geometrically consistent mappings between 3D shapes. We use the mathematically elegant forma…
Structured Prediction Problem Archive
Paul Swoboda, Bjoern Andres, Andrea Hornakova +6
Structured prediction problems are one of the fundamental tools in machine learning. In order to facilitate algorithm development for their numerical solution, we collect in one pl…
LMGP: Lifted Multicut Meets Geometry Projections for Multi-Camera Multi-Object Tracking
Duy M. H. Nguyen, Roberto Henschel, Bodo Rosenhahn +2
Multi-Camera Multi-Object Tracking is currently drawing attention in the computer vision field due to its superior performance in real-world applications such as video surveillance…
FastDOG: Fast Discrete Optimization on GPU
Ahmed Abbas, Paul Swoboda
We present a massively parallel Lagrange decomposition method for solving 0--1 integer linear programs occurring in structured prediction. We propose a new iterative update scheme…
RAMA: A Rapid Multicut Algorithm on GPU
Ahmed Abbas, Paul Swoboda
We propose a highly parallel primal-dual algorithm for the multicut (a.k.a. correlation clustering) problem, a classical graph clustering problem widely used in machine learning an…
Making Higher Order MOT Scalable: An Efficient Approximate Solver for Lifted Disjoint Paths
Andrea Hornakova, Timo Kaiser, Paul Swoboda +3
We present an efficient approximate message passing solver for the lifted disjoint paths problem (LDP), a natural but NP-hard model for multiple object tracking (MOT). Our tracker…
Combinatorial Optimization for Panoptic Segmentation: A Fully Differentiable Approach
Ahmed Abbas, Paul Swoboda
We propose a fully differentiable architecture for simultaneous semantic and instance segmentation (a.k.a. panoptic segmentation) consisting of a convolutional neural network and a…
Efficient Message Passing for 0-1 ILPs with Binary Decision Diagrams
Jan-Hendrik Lange, Paul Swoboda
We present a message passing method for 0-1 integer linear programs. Our algorithm is based on a decomposition of the original problem into subproblems that are represented as bina…
Lifted Disjoint Paths with Application in Multiple Object Tracking
Andrea Hornakova, Roberto Henschel, Bodo Rosenhahn +1
We present an extension to the disjoint paths problem in which additional \emph{lifted} edges are introduced to provide path connectivity priors. We call the resulting optimization…
A Primal-Dual Solver for Large-Scale Tracking-by-Assignment
Stefan Haller, Mangal Prakash, Lisa Hutschenreiter +5
We propose a fast approximate solver for the combinatorial problem known as tracking-by-assignment, which we apply to cell tracking. The latter plays a key role in discovery in man…
Exact MAP-Inference by Confining Combinatorial Search with LP Relaxation
Stefan Haller, Paul Swoboda, Bogdan Savchynskyy
We consider the MAP-inference problem for graphical models, which is a valued constraint satisfaction problem defined on real numbers with a natural summation operation. We propose…
Deep Graph Matching via Blackbox Differentiation of Combinatorial Solvers
Michal Rolínek, Paul Swoboda, Dominik Zietlow +3
Building on recent progress at the intersection of combinatorial optimization and deep learning, we propose an end-to-end trainable architecture for deep graph matching that contai…
Bottleneck potentials in Markov Random Fields
Ahmed Abbas, Paul Swoboda
We consider general discrete Markov Random Fields(MRFs) with additional bottleneck potentials which penalize the maximum (instead of the sum) over local potential value taken by th…
Combinatorial persistency criteria for multicut and max-cut
Jan-Hendrik Lange, Bjoern Andres, Paul Swoboda
In combinatorial optimization, partial variable assignments are called persistent if they agree with some optimal solution. We propose persistency criteria for the multicut and max…
Higher-order Projected Power Iterations for Scalable Multi-Matching
Florian Bernard, Johan Thunberg, Paul Swoboda +1
The matching of multiple objects (e.g. shapes or images) is a fundamental problem in vision and graphics. In order to robustly handle ambiguities, noise and repetitive patterns in…
MAP inference via Block-Coordinate Frank-Wolfe Algorithm
Paul Swoboda, Vladimir Kolmogorov
We present a new proximal bundle method for Maximum-A-Posteriori (MAP) inference in structured energy minimization problems. The method optimizes a Lagrangean relaxation of the ori…