%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 Universität des Saarlandes %C Saarbrücken %D 2018 %P X, 57 p. %V master %9 master

%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 RAMA: A Rapid Multicut Algorithm on GPU : %G eng %U http://hdl.handle.net/21.11116/0000-0009-B3E6-9 %U https://arxiv.org/abs/2109.01838 %D 2021 %X 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 and computer vision. Our algorithm consists of three steps executed recursively: (1) Finding conflicted cycles that correspond to violated inequalities of the underlying multicut relaxation, (2) Performing message passing between the edges and cycles to optimize the Lagrange relaxation coming from the found violated cycles producing reduced costs and (3) Contracting edges with high reduced costs through matrix-matrix multiplications. Our algorithm produces primal solutions and dual lower bounds that estimate the distance to optimum. We implement our algorithm on GPUs and show resulting one to two order-of-magnitudes improvements in execution speed without sacrificing solution quality compared to traditional serial algorithms that run on CPUs. We can solve very large scale benchmark problems with up to $\mathcal{O}(10^8)$ variables in a few seconds with small primal-dual gaps. We make our code available at https://github.com/pawelswoboda/RAMA. %K Computer Science, Distributed, Parallel, and Cluster Computing, cs.DC,Computer Science, Computer Vision and Pattern Recognition, cs.CV,Computer Science, Data Structures and Algorithms, cs.DS,Computer Science, Learning, cs.LG

%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

%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 integer linear programs occurring in structured prediction. We propose a new iterative update scheme for solving the Lagrangean dual and a perturbation technique for decoding primal solutions. For representing subproblems we follow Lange et al. (2021) and use binary decision diagrams (BDDs). Our primal and dual algorithms require little synchronization between subproblems and optimization over BDDs needs only elementary operations without complicated control flow. This allows us to exploit the parallelism offered by GPUs for all components of our method. We present experimental results on combinatorial problems from MAP inference for Markov Random Fields, quadratic assignment and cell tracking for developmental biology. Our highly parallel GPU implementation improves upon the running times of the algorithms from Lange et al. (2021) by up to an order of magnitude. In particular, we come close to or outperform some state-of-the-art specialized heuristics while being problem agnostic. %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

%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

%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.

%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

%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 bottleneck potentials which penalize the maximum (instead of the sum) over local potential value taken by the MRF-assignment. Bottleneck potentials or analogous constructions have been considered in (i) combinatorial optimization (e.g. bottleneck shortest path problem, the minimum bottleneck spanning tree problem, bottleneck function minimization in greedoids), (ii) inverse problems with $L_{\infty}$-norm regularization, and (iii) valued constraint satisfaction on the $(\min,\max)$-pre-semirings. Bottleneck potentials for general discrete MRFs are a natural generalization of the above direction of modeling work to Maximum-A-Posteriori (MAP) inference in MRFs. To this end, we propose MRFs whose objective consists of two parts: terms that factorize according to (i) $(\min,+)$, i.e. potentials as in plain MRFs, and (ii) $(\min,\max)$, i.e. bottleneck potentials. To solve the ensuing inference problem, we propose high-quality relaxations and efficient algorithms for solving them. We empirically show efficacy of our approach on large scale seismic horizon tracking problems. %K Computer Science, Computer Vision and Pattern Recognition, cs.CV