# Ahmed Abbas (PhD Student)

## MSc Ahmed Abbas

Max-Planck-Institut für Informatik
Saarland Informatics Campus
Campus E1 4
66123 Saarbrücken
Standort
E1 4 - 629
Telefon
+49 681 9325 2147
Fax
+49 681 9325 2099

# Publications

Abbas, A. (2018). Bottleneck Potentials in Markov Random Fields. Universität des Saarlandes, Saarbrücken.
Export
BibTeX
@mastersthesis{Abbas_Master2019, TITLE = {Bottleneck Potentials in Markov Random Fields}, AUTHOR = {Abbas, Ahmed}, LANGUAGE = {eng}, SCHOOL = {Universit{\"a}t des Saarlandes}, ADDRESS = {Saarbr{\"u}cken}, YEAR = {2018}, DATE = {2018}, }
Endnote
%0 Thesis %A Abbas, Ahmed %A referee: Schiele, Bernt %Y Swoboda, Paul %+ Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society %T Bottleneck Potentials in Markov Random Fields : %G eng %U http://hdl.handle.net/21.11116/0000-0003-9192-3 %I Universit&#228;t des Saarlandes %C Saarbr&#252;cken %D 2018 %P X, 57 p. %V master %9 master
Abbas, A., & Swoboda, P. (2022a). RAMA: A Rapid Multicut Algorithm on GPU. In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022). New Orleans, LA, USA: IEEE. doi:10.1109/CVPR52688.2022.00802
Export
BibTeX
@inproceedings{Abbas_CVPR22, TITLE = {{RAMA}: {A} Rapid Multicut Algorithm on {GPU}}, AUTHOR = {Abbas, Ahmed and Swoboda, Paul}, LANGUAGE = {eng}, ISBN = {978-1-6654-6946-3}, DOI = {10.1109/CVPR52688.2022.00802}, PUBLISHER = {IEEE}, YEAR = {2022}, MARGINALMARK = {$\bullet$}, BOOKTITLE = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022)}, PAGES = {8183--8192}, ADDRESS = {New Orleans, LA, USA}, }
Endnote
%0 Conference Proceedings %A Abbas, Ahmed %A Swoboda, Paul %+ Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society %T RAMA: A Rapid Multicut Algorithm on GPU : %G eng %U http://hdl.handle.net/21.11116/0000-0009-B3E6-9 %R 10.1109/CVPR52688.2022.00802 %D 2022 %B 35th IEEE/CVF Conference on Computer Vision and Pattern Recognition %Z date of event: 2022-06-19 - 2022-06-24 %C New Orleans, LA, USA %B IEEE/CVF Conference on Computer Vision and Pattern Recognition %P 8183 - 8192 %I IEEE %@ 978-1-6654-6946-3
Abbas, A., & Swoboda, P. (2019a). Bottleneck Potentials in Markov Random Fields. In International Conference on Computer Vision (ICCV 2019). Seoul, Korea: IEEE. doi:10.1109/ICCV.2019.00327
Export
BibTeX
@inproceedings{Abbas_ICCV2019, TITLE = {Bottleneck Potentials in {Markov Random Fields}}, AUTHOR = {Abbas, Ahmed and Swoboda, Paul}, LANGUAGE = {eng}, ISBN = {978-1-7281-4803-8}, DOI = {10.1109/ICCV.2019.00327}, PUBLISHER = {IEEE}, YEAR = {2019}, DATE = {2019}, BOOKTITLE = {International Conference on Computer Vision (ICCV 2019)}, PAGES = {3174--3183}, ADDRESS = {Seoul, Korea}, }
Endnote
%0 Conference Proceedings %A Abbas, Ahmed %A Swoboda, Paul %+ Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society %T Bottleneck Potentials in Markov Random Fields : %G eng %U http://hdl.handle.net/21.11116/0000-0006-DC7E-6 %R 10.1109/ICCV.2019.00327 %D 2019 %B International Conference on Computer Vision %Z date of event: 2019-10-27 - 2019-11-02 %C Seoul, Korea %B International Conference on Computer Vision %P 3174 - 3183 %I IEEE %@ 978-1-7281-4803-8
Abbas, A., & Swoboda, P. (2021a). FastDOG: Fast Discrete Optimization on GPU. Retrieved from https://arxiv.org/abs/2111.10270
(arXiv: 2111.10270)
Abstract
We present a massively parallel Lagrange decomposition method for solving 0-1<br>integer linear programs occurring in structured prediction. We propose a new<br>iterative update scheme for solving the Lagrangean dual and a perturbation<br>technique for decoding primal solutions. For representing subproblems we follow<br>Lange et al. (2021) and use binary decision diagrams (BDDs). Our primal and<br>dual algorithms require little synchronization between subproblems and<br>optimization over BDDs needs only elementary operations without complicated<br>control flow. This allows us to exploit the parallelism offered by GPUs for all<br>components of our method. We present experimental results on combinatorial<br>problems from MAP inference for Markov Random Fields, quadratic assignment and<br>cell tracking for developmental biology. Our highly parallel GPU implementation<br>improves upon the running times of the algorithms from Lange et al. (2021) by<br>up to an order of magnitude. In particular, we come close to or outperform some<br>state-of-the-art specialized heuristics while being problem agnostic.<br>
Export
BibTeX
@online{Abbas_2111.10270, TITLE = {{FastDOG}: {F}ast Discrete Optimization on {GPU}}, AUTHOR = {Abbas, Ahmed and Swoboda, Paul}, LANGUAGE = {eng}, URL = {https://arxiv.org/abs/2111.10270}, EPRINT = {2111.10270}, EPRINTTYPE = {arXiv}, YEAR = {2021}, MARGINALMARK = {$\bullet$}, ABSTRACT = {We present a massively parallel Lagrange decomposition method for solving 0-1<br>integer linear programs occurring in structured prediction. We propose a new<br>iterative update scheme for solving the Lagrangean dual and a perturbation<br>technique for decoding primal solutions. For representing subproblems we follow<br>Lange et al. (2021) and use binary decision diagrams (BDDs). Our primal and<br>dual algorithms require little synchronization between subproblems and<br>optimization over BDDs needs only elementary operations without complicated<br>control flow. This allows us to exploit the parallelism offered by GPUs for all<br>components of our method. We present experimental results on combinatorial<br>problems from MAP inference for Markov Random Fields, quadratic assignment and<br>cell tracking for developmental biology. Our highly parallel GPU implementation<br>improves upon the running times of the algorithms from Lange et al. (2021) by<br>up to an order of magnitude. In particular, we come close to or outperform some<br>state-of-the-art specialized heuristics while being problem agnostic.<br>}, }
Endnote
%0 Report %A Abbas, Ahmed %A Swoboda, Paul %+ Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society %T FastDOG: Fast Discrete Optimization on GPU : %G eng %U http://hdl.handle.net/21.11116/0000-0009-B3EA-5 %U https://arxiv.org/abs/2111.10270 %D 2021 %X We present a massively parallel Lagrange decomposition method for solving 0-1<br>integer linear programs occurring in structured prediction. We propose a new<br>iterative update scheme for solving the Lagrangean dual and a perturbation<br>technique for decoding primal solutions. For representing subproblems we follow<br>Lange et al. (2021) and use binary decision diagrams (BDDs). Our primal and<br>dual algorithms require little synchronization between subproblems and<br>optimization over BDDs needs only elementary operations without complicated<br>control flow. This allows us to exploit the parallelism offered by GPUs for all<br>components of our method. We present experimental results on combinatorial<br>problems from MAP inference for Markov Random Fields, quadratic assignment and<br>cell tracking for developmental biology. Our highly parallel GPU implementation<br>improves upon the running times of the algorithms from Lange et al. (2021) by<br>up to an order of magnitude. In particular, we come close to or outperform some<br>state-of-the-art specialized heuristics while being problem agnostic.<br> %K Mathematics, Optimization and Control, math.OC,Computer Science, Computer Vision and Pattern Recognition, cs.CV,Computer Science, Distributed, Parallel, and Cluster Computing, cs.DC,Computer Science, Computer Science and Game Theory, cs.GT
Swoboda, P., Horňáková, A., Rötzer, P., Savchynskyy, B., & Abbas, A. (2022). Structured Prediction Problem Archive. Retrieved from https://arxiv.org/abs/2202.03574
(arXiv: 2202.03574)
Abstract
Structured prediction problems are one of the fundamental tools in machine<br>learning. In order to facilitate algorithm development for their numerical<br>solution, we collect in one place a large number of datasets in easy to read<br>formats for a diverse set of problem classes. We provide archival links to<br>datasets, description of the considered problems and problem formats, and a<br>short summary of problem characteristics including size, number of instances<br>etc. For reference we also give a non-exhaustive selection of algorithms<br>proposed in the literature for their solution. We hope that this central<br>repository will make benchmarking and comparison to established works easier.<br>We welcome submission of interesting new datasets and algorithms for inclusion<br>in our archive.<br>
Export
BibTeX
@online{Swoboda2202.03574, TITLE = {Structured Prediction Problem Archive}, AUTHOR = {Swoboda, Paul and Hor{\v n}{\'a}kov{\'a}, Andrea and R{\"o}tzer, Paul and Savchynskyy, Bogdan and Abbas, Ahmed}, LANGUAGE = {eng}, URL = {https://arxiv.org/abs/2202.03574}, EPRINT = {2202.03574}, EPRINTTYPE = {arXiv}, YEAR = {2022}, MARGINALMARK = {$\bullet$}, ABSTRACT = {Structured prediction problems are one of the fundamental tools in machine<br>learning. In order to facilitate algorithm development for their numerical<br>solution, we collect in one place a large number of datasets in easy to read<br>formats for a diverse set of problem classes. We provide archival links to<br>datasets, description of the considered problems and problem formats, and a<br>short summary of problem characteristics including size, number of instances<br>etc. For reference we also give a non-exhaustive selection of algorithms<br>proposed in the literature for their solution. We hope that this central<br>repository will make benchmarking and comparison to established works easier.<br>We welcome submission of interesting new datasets and algorithms for inclusion<br>in our archive.<br>}, }
Endnote
%0 Report %A Swoboda, Paul %A Hor&#328;&#225;kov&#225;, Andrea %A R&#246;tzer, Paul %A Savchynskyy, Bogdan %A Abbas, Ahmed %+ Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society External Organizations Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society %T Structured Prediction Problem Archive : %G eng %U http://hdl.handle.net/21.11116/0000-000C-2AAA-6 %U https://arxiv.org/abs/2202.03574 %D 2022 %X Structured prediction problems are one of the fundamental tools in machine<br>learning. In order to facilitate algorithm development for their numerical<br>solution, we collect in one place a large number of datasets in easy to read<br>formats for a diverse set of problem classes. We provide archival links to<br>datasets, description of the considered problems and problem formats, and a<br>short summary of problem characteristics including size, number of instances<br>etc. For reference we also give a non-exhaustive selection of algorithms<br>proposed in the literature for their solution. We hope that this central<br>repository will make benchmarking and comparison to established works easier.<br>We welcome submission of interesting new datasets and algorithms for inclusion<br>in our archive.<br> %K Computer Science, Learning, cs.LG,Computer Science, Computer Vision and Pattern Recognition, cs.CV
Abbas, A., Nadeem, M., & Shafiq, A. (2014). Detection of Isotropic Regions and Enhancement of Fault Attributes in Seismic Volumes. SEG Technical Program Expanded Abstracts, 2014. doi:10.1190/segam2014-0425.1
Export
BibTeX
@article{Abbas2014, TITLE = {Detection of Isotropic Regions and Enhancement of Fault Attributes in Seismic Volumes}, AUTHOR = {Abbas, Ahmed and Nadeem, Mehak and Shafiq, Arsalan}, LANGUAGE = {eng}, ISSN = {1052-3812}, DOI = {10.1190/segam2014-0425.1}, PUBLISHER = {Society of Exploration Geophysicists}, YEAR = {2014}, DATE = {2014}, JOURNAL = {SEG Technical Program Expanded Abstracts}, VOLUME = {2014}, PAGES = {1420--1423}, }
Endnote
%0 Journal Article %A Abbas, Ahmed %A Nadeem, Mehak %A Shafiq, Arsalan %+ External Organizations External Organizations External Organizations %T Detection of Isotropic Regions and Enhancement of Fault Attributes in Seismic Volumes : %G eng %U http://hdl.handle.net/21.11116/0000-0007-1EF4-5 %R 10.1190/segam2014-0425.1 %7 2014 %D 2014 %J SEG Technical Program Expanded Abstracts %V 2014 %& 1420 %P 1420 - 1423 %I Society of Exploration Geophysicists %@ false
Abbas, A., Abbasi, H., & Shafiq, A. (2015). Enhancement of Subtle Features in Coherence Volumes. SEG Technical Program Expanded Abstracts, 2015. doi:10.1190/segam2015-5901251.1
Export
BibTeX
@article{Abbas2015, TITLE = {Enhancement of Subtle Features in Coherence Volumes}, AUTHOR = {Abbas, Ahmed and Abbasi, Hameer and Shafiq, Arsalan}, LANGUAGE = {eng}, ISSN = {1052-3812}, DOI = {10.1190/segam2015-5901251.1}, PUBLISHER = {Society of Exploration Geophysicists}, YEAR = {2015}, DATE = {2015}, JOURNAL = {SEG Technical Program Expanded Abstracts}, VOLUME = {2015}, PAGES = {1707--1710}, }
Endnote
%0 Journal Article %A Abbas, Ahmed %A Abbasi, Hameer %A Shafiq, Arsalan %+ External Organizations External Organizations External Organizations %T Enhancement of Subtle Features in Coherence Volumes : %G eng %U http://hdl.handle.net/21.11116/0000-0007-1EF1-8 %R 10.1190/segam2015-5901251.1 %7 2015 %D 2015 %J SEG Technical Program Expanded Abstracts %V 2015 %& 1707 %P 1707 - 1710 %I Society of Exploration Geophysicists %@ false
Abbas, A., & Swoboda, P. (2022b). FastDOG: Fast Discrete Optimization on GPU. In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022). New Orleans, LA, USA: IEEE. doi:10.1109/CVPR52688.2022.00053
Export
BibTeX
@inproceedings{Abbas_CVPR22x, TITLE = {{FastDOG}: {F}ast Discrete Optimization on {GPU}}, AUTHOR = {Abbas, Ahmed and Swoboda, Paul}, LANGUAGE = {eng}, ISBN = {978-1-6654-6946-3}, DOI = {10.1109/CVPR52688.2022.00053}, PUBLISHER = {IEEE}, YEAR = {2022}, MARGINALMARK = {$\bullet$}, BOOKTITLE = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022)}, PAGES = {439--449}, ADDRESS = {New Orleans, LA, USA}, }
Endnote
%0 Conference Proceedings %A Abbas, Ahmed %A Swoboda, Paul %+ Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society %T FastDOG: Fast Discrete Optimization on GPU : %G eng %U http://hdl.handle.net/21.11116/0000-000C-11FF-2 %R 10.1109/CVPR52688.2022.00053 %D 2022 %B 35th IEEE/CVF Conference on Computer Vision and Pattern Recognition %Z date of event: 2022-06-19 - 2022-06-24 %C New Orleans, LA, USA %B IEEE/CVF Conference on Computer Vision and Pattern Recognition %P 439 - 449 %I IEEE %@ 978-1-6654-6946-3
Abbas, A., & Swoboda, P. (2021b). Combinatorial Optimization for Panoptic Segmentation: A Fully Differentiable Approach. In Advances in Neural Information Processing Systems 34 pre-proceedings (NeurIPS 2021). Virtual: Curran Associates, Inc.
Export
BibTeX
@inproceedings{Abbas_Neurips2021, TITLE = {Combinatorial Optimization for Panoptic Segmentation: {A} Fully Differentiable Approach}, AUTHOR = {Abbas, Ahmed and Swoboda, Paul}, LANGUAGE = {eng}, PUBLISHER = {Curran Associates, Inc.}, YEAR = {2021}, MARGINALMARK = {$\bullet$}, BOOKTITLE = {Advances in Neural Information Processing Systems 34 pre-proceedings (NeurIPS 2021)}, EDITOR = {Ranzato, M. and Beygelzimer, A. and Liang, P. S. and Vaughan, J. W. and Dauphin, Y.}, ADDRESS = {Virtual}, }
Endnote
%0 Conference Proceedings %A Abbas, Ahmed %A Swoboda, Paul %+ Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society %T Combinatorial Optimization for Panoptic Segmentation: A Fully Differentiable Approach : %G eng %U http://hdl.handle.net/21.11116/0000-0009-B3DC-5 %D 2021 %B 35th Conference on Neural Information Processing Systems %Z date of event: 2021-12-07 - 2021-12-07 %C Virtual %B Advances in Neural Information Processing Systems 34 pre-proceedings %E Ranzato, M.; Beygelzimer, A.; Liang, P. S.; Vaughan, J. W.; Dauphin, Y. %I Curran Associates, Inc.
Abbas, A., & Swoboda, P. (2019b). Bottleneck Potentials in Markov Random Fields. Retrieved from http://arxiv.org/abs/1904.08080
(arXiv: 1904.08080)
Abstract
We consider general discrete Markov Random Fields(MRFs) with additional<br>bottleneck potentials which penalize the maximum (instead of the sum) over<br>local potential value taken by the MRF-assignment. Bottleneck potentials or<br>analogous constructions have been considered in (i) combinatorial optimization<br>(e.g. bottleneck shortest path problem, the minimum bottleneck spanning tree<br>problem, bottleneck function minimization in greedoids), (ii) inverse problems<br>with $L_{\infty}$-norm regularization, and (iii) valued constraint satisfaction<br>on the $(\min,\max)$-pre-semirings. Bottleneck potentials for general discrete<br>MRFs are a natural generalization of the above direction of modeling work to<br>Maximum-A-Posteriori (MAP) inference in MRFs. To this end, we propose MRFs<br>whose objective consists of two parts: terms that factorize according to (i)<br>$(\min,+)$, i.e. potentials as in plain MRFs, and (ii) $(\min,\max)$, i.e.<br>bottleneck potentials. To solve the ensuing inference problem, we propose<br>high-quality relaxations and efficient algorithms for solving them. We<br>empirically show efficacy of our approach on large scale seismic horizon<br>tracking problems.<br>
Export
BibTeX
@online{DBLP:journals/corr/abs-1904-08080, TITLE = {Bottleneck Potentials in {Markov Random Fields}}, AUTHOR = {Abbas, Ahmed and Swoboda, Paul}, LANGUAGE = {eng}, URL = {http://arxiv.org/abs/1904.08080}, EPRINT = {1904.08080}, EPRINTTYPE = {arXiv}, YEAR = {2019}, ABSTRACT = {We consider general discrete Markov Random Fields(MRFs) with additional<br>bottleneck potentials which penalize the maximum (instead of the sum) over<br>local potential value taken by the MRF-assignment. Bottleneck potentials or<br>analogous constructions have been considered in (i) combinatorial optimization<br>(e.g. bottleneck shortest path problem, the minimum bottleneck spanning tree<br>problem, bottleneck function minimization in greedoids), (ii) inverse problems<br>with $L_{\infty}$-norm regularization, and (iii) valued constraint satisfaction<br>on the $(\min,\max)$-pre-semirings. Bottleneck potentials for general discrete<br>MRFs are a natural generalization of the above direction of modeling work to<br>Maximum-A-Posteriori (MAP) inference in MRFs. To this end, we propose MRFs<br>whose objective consists of two parts: terms that factorize according to (i)<br>$(\min,+)$, i.e. potentials as in plain MRFs, and (ii) $(\min,\max)$, i.e.<br>bottleneck potentials. To solve the ensuing inference problem, we propose<br>high-quality relaxations and efficient algorithms for solving them. We<br>empirically show efficacy of our approach on large scale seismic horizon<br>tracking problems.<br>}, }
Endnote
%0 Report %A Abbas, Ahmed %A Swoboda, Paul %+ Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society %T Bottleneck Potentials in Markov Random Fields : %G eng %U http://hdl.handle.net/21.11116/0000-0003-9D88-3 %U http://arxiv.org/abs/1904.08080 %D 2019 %X We consider general discrete Markov Random Fields(MRFs) with additional<br>bottleneck potentials which penalize the maximum (instead of the sum) over<br>local potential value taken by the MRF-assignment. Bottleneck potentials or<br>analogous constructions have been considered in (i) combinatorial optimization<br>(e.g. bottleneck shortest path problem, the minimum bottleneck spanning tree<br>problem, bottleneck function minimization in greedoids), (ii) inverse problems<br>with $L_{\infty}$-norm regularization, and (iii) valued constraint satisfaction<br>on the $(\min,\max)$-pre-semirings. Bottleneck potentials for general discrete<br>MRFs are a natural generalization of the above direction of modeling work to<br>Maximum-A-Posteriori (MAP) inference in MRFs. To this end, we propose MRFs<br>whose objective consists of two parts: terms that factorize according to (i)<br>$(\min,+)$, i.e. potentials as in plain MRFs, and (ii) $(\min,\max)$, i.e.<br>bottleneck potentials. To solve the ensuing inference problem, we propose<br>high-quality relaxations and efficient algorithms for solving them. We<br>empirically show efficacy of our approach on large scale seismic horizon<br>tracking problems.<br> %K Computer Science, Computer Vision and Pattern Recognition, cs.CV