My research

• Compete on computer vision benchmarks (multiple object tracking, keypoint matching, segmentation)
• Make (discrete) optimization work for machine learning and computer vision
• Develop my own general purpose ILP solver
• Use machine learning to improve optimization solvers

---

Publications google scholar profile »

• ICCV'23 "A Multidimensional Analysis of Social Biases in Vision Transformers", Brinkmann, Jannik and Swoboda, Paul and Bartelt, Christian IEEE International Conference on Computer Vision (ICCV) 2023
• CVPR'23 "ClusterFuG: Clustering Fully connected Graphs by Multicut", Abbas, Ahmed and Swoboda, Paul, IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2023
• AAAI'22 "Joint Self-Supervised Image-Volume Representation Learning with Intra-Inter Contrastive Clustering", Nguyen, Duy M. H. and Nguyen, Hoang and Truong, Mai T. N. and Cao, Tri and Nguyen, Binh T. and Ho, Nhat and Swoboda, Paul and Albarqouni, Shadi and Xie, Pengtao and Sonntag, Daniel, Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI) 2023
• ECCV'22 "A Comparative Study of Graph Matching Algorithms in Computer Vision", Haller, Stefan and Feineis, Lorenz and Hutschenreiter, Lisa and Bernard, Florian and Rother, Carsten and Kainmuller, Dagmar and Swoboda, Paul and Savchynskyy, Bogdan, IEEE European Conference on Computer Vision (ECCV) 2022
• Arxiv'22 "DOGE-Train: Discrete Optimization on GPU with End-to-end Training", Abbas, Ahmed and Swoboda, Paul, Arxiv 2022
• Arxiv'22 "Structured Prediction Problem Archive", Swoboda, Paul and Hornakova, Andrea and Roetzer, Paul and Savchynskyy, Bogdan and Abbas, Ahmed, Arxiv 2022
• CVPR'22 "FastDOG: Fast Discrete Optimization on GPU", Abbas, Ahmed and Swoboda, Paul, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2022
• CVPR'22 "RAMA: A Rapid Multicut Algorithm on GPU", Abbas, Ahmed and Swoboda, Paul, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2022
• CVPR'22 "LMGP: Lifted Multicut Meets Geometry Projections for Multi-Camera Multi-Object Tracking", Nguyen, Duy M. H. and Henschel, Roberto and Rosenhahn, Bodo and Sonntag, Daniel and Swoboda, Paul, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2022
• CVPR'22 "A Scalable Combinatorial Solver for Elastic Geometrically Consistent 3D Shape Matching", Roetzer, Paul and Swoboda, Paul and Cremers, Daniel and Bernard, Florian, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2022
• NeurIPS'21 "Combinatorial Optimization for Panoptic Segmentation: A Fully Differentiable Approach", Abbas, Ahmed and Swoboda, Paul, Proceedings of the Advances in Neural Information Processing Systems (NeurIPS) 2021
• ICCV'21 "Making Higher Order MOT Scalable: An Efficient Approximate Solver for Lifted Disjoint Paths", Hornakova, Andrea and Kaiser, Timo and Swoboda, Paul and Rolinek, Michal and Rosenhahn, Bodo and Henschel, Roberto, Proceedings of the IEEE International Conference on Computer Vision (ICCV) 2021
• ICML'21 "Efficient Message Passing for 0-1 {ILPs} with Binary Decision Diagrams", Lange, Jan-Hendrik and Swoboda, Paul, Proceedings of the International Conference on Machine Learning (ICML) 2021
• ECCV'20 "Deep Graph Matching via Blackbox Differentiation of Combinatorial Solvers", Rolínek, Michal and Swoboda, Paul and Zietlow, Dominik and Paulus, Anselm and Musil, Vít and Martius, Georg, Proceedings of the IEEE European Conference on Computer Vision (ECCV) 2020
• ICML'20 "Lifted Disjoint Paths with Application in Multiple Object Tracking", Hornakova, Andrea and Henschel, Roberto and Rosenhahn, Bodo and Swoboda, Paul, Proceedings of the International Conference on Machine Learning (ICML) 2020
• AISTATS'20 "A Primal-Dual Solver for Large-Scale Tracking-by-Assignment", Haller, Stefan and Prakash, Mangal and Hutschenreiter, Lisa and Pietzsch, Tobias and Rother, Carsten and Jug, Florian and Swoboda, Paul and Savchynskyy, Bogdan, Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS) 2020
• ICCV'19 "Bottleneck potentials in Markov Random Fields", Abbas, Ahmed and Swoboda, Paul, Proceedings of the Proceedings of the IEEE International Conference on Computer Vision (ICCV) 2019
• ICCV'19 "Higher-order Projected Power Iterations for Scalable Multi-Matching", Bernard, Florian and Thunberg, Johan and Swoboda, Paul and Theobalt, Christian, Proceedings of the IEEE International Conference on Computer Vision (ICCV) 2019
• CVPR'19 "A Convex Relaxation for Multi-Graph Matching", Swoboda, Paul and Mokarian, Ashkan and Theobalt, Christian and Bernard, Florian and others, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2019
• CVPR'19 "Combinatorial persistency criteria for multicut and max-cut", Lange, Jan-Hendrik and Andres, Bjoern and Swoboda, Paul, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2019
• CVPR'19 "MAP inference via Block-Coordinate Frank-Wolfe Algorithm", Swoboda, Paul and Kolmogorov, Vladimir, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2019
• AAAI'18 "Exact MAP-Inference by Confining Combinatorial Search with LP Relaxation", Haller, Stefan and Swoboda, Paul and Savchynskyy, Bogdan, Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence 2018
• SSVM'17 "A novel convex relaxation for non-binary discrete tomography", Kuske, Jan and Swoboda, Paul and Petra, Stefania, International Conference on Scale Space and Variational Methods in Computer Vision (SSVM) 2017
• CVPR'17 "A Study of Lagrangean Decompositions and Dual Ascent Solvers for Graph Matching"Swoboda, Paul and Rother, Carsten and Abu Alhaija, Hassan and Kainmuller, Dagmar and Savchynskyy, Bogdan, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017
• CVPR'17 "A message passing algorithm for the minimum cost multicut problem", Swoboda, Paul and Andres, Bjoern, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017
• CVPR'17 "A Dual Ascent Framework for Lagrangean Decomposition of Combinatorial Problems", Swoboda, Paul and Kuske, Jan and Savchynskyy, Bogdan, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017
• TPAMI'16 "Partial Optimality by Pruning for MAP", Swoboda, Paul and Shekhovtsov, Alexander and Kappes, Jörg Hendrik and Schnörr, Christoph and Savchynskyy, Bogdan, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2016
• JMIV'16 "Multicuts and Perturb & MAP for Probabilistic Graph Clustering", Kappes, Jörg Hendrik and Swoboda, Paul and Savchynskyy, Bogdan and Hazan, Tamir and Schnörr, Christoph, Journal of Mathematical Imaging and Vision (JMIV) 2016
• CVPR'15 "Maximum Persistency via Iterative Relaxed Inference with Graphical Models", Shekhovtsov, Alexander and Swoboda, Paul and Savchynskyy, Bogdan, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2015
• SSVM'15 "Maximum Persistency via Iterative Relaxed Inference with Graphical Models", Kappes, Jörg Hendrik and Swoboda, Paul and Savchynskyy, Bogdan and Hazan, Tamir and Schnörr, Christoph, International Conference on Scale Space and Variational Methods in Computer Vision (SSVM) 2015
• CVPR'14 "Partial optimality by pruning for MAP", Swoboda, Paul and Savchynskyy, Bogdan and Kappes, Jörg H and Schnörr, Christoph, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2014, Best student paper award
• SIAM-IS'13 "Convex Variational Image Restoration with Histogram Priors", Swoboda, Paul and Schnörr, Christoph, SIAM Journal on Imaging Sciences 2013
• NIPS'13 "Global MAP-Optimality by Shrinking the Combinatorial Search Area with Convex Relaxation", Savchynskyy, Bogdan and Kappes, Jörg Hendrik and Swoboda, Paul and Schnörr, Christoph, Advances in Neural Information Processing Systems (NIPS) 2013
• SSVM'13 "Partial optimality via iterative pruning for the Potts model,", Swoboda, Paul and Savchynskyy, Bogdan and Kappes, Jörg H and Schnörr, Christoph, International Conference on Scale Space and Variational Methods in Computer Vision (SSVM) 2013

---

Group Members

• PhD Jannik Brinkmann, PhD student at Mannheim University
• PhD Ahmed Abbas, PhD student at MPI-INF
• PhD (completed) Andrea Hornakova, PhD student at MPI-INF
• PhD (completed) Jan-Hendrik Lange, PhD student at MPI-INF

---

Open Position

We offer a PhD position for exceptionally gifted students. The position is fully funded (E13 TV-L) at the Heinrich Heine University Düsseldorf, Germany.

• Tasks: Curiosity-driven basic research of fundamental problems in machine learning. Exemplary research areas include, but are not limited to, theoretically principled improvement of machine learning models, machine learning for optimization and efficient GPU algorithms.
• Requirements: Very good university degree in mathematics, computer science or a related discipline, good programming skills, preferably python and C++.

---

Contact

---