This is an old revision of the document!
% generated by bibtexbrowser
%
% Encoding: UTF-8
@inproceedings{moellenhoff-et-al-13,
author = {T. Möllenhoff and C. Nieuwenhuis and E. Toeppe and D. Cremers},
title = {Efficient Convex Optimization for Minimal Partition Problems with Volume Constraints},
booktitle = {Energy Minimization Methods in Computer Vision and Pattern Recognition (EMMCVPR)},
year = {2013},
titleurl = {moellenhoff_et_al_13.pdf},
keywords = {convex-relaxation},
}
@inproceedings{moellenhoff-et-al-15,
author = {T. Möllenhoff and E. Strekalovskiy and M. Möller and D. Cremers},
title = {Low Rank Priors for Color Image Regularization},
booktitle = {Energy Minimization Methods in Computer Vision and Pattern Recognition (EMMCVPR)},
year = {2015},
titleurl = {moellenhoff_et_al_15.pdf},
}
@article{moellenhoff-siims-15,
author = {T. Möllenhoff and E. Strekalovskiy and M. Möller and D. Cremers},
title = {The Primal-Dual Hybrid Gradient Method for Semiconvex Splittings},
journal = {SIAM Journal on Imaging Sciences},
year = {2015},
volume = {8},
number = {2},
pages = {827-857},
titleurl = {moellenhoff_et_al_siims15.pdf},
}
@inproceedings{moellenhoff-laude-cvpr16,
author = {T. Möllenhoff and E. Laude and M. Moeller and J. Lellmann and D. Cremers},
title = {Sublabel-Accurate Relaxation of Nonconvex Energies},
booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
year = {2016},
titleurl = {moellenhoff_laude_cvpr_16.pdf},
keywords = {convex-relaxation},
award = {Oral Presentation, Received the Best Paper Honorable Mention Award at CVPR 2016},
}
@inproceedings{laude16eccv,
author = {E. Laude and T. Möllenhoff and M. Moeller and J. Lellmann and D. Cremers},
title = {Sublabel-Accurate Convex Relaxation of Vectorial Multilabel Energies},
year = {2016},
month = {October},
booktitle = {European Conference on Computer Vision (ECCV)},
keywords = {convex-optimization, convex-relaxation, multilabeling, primal-dual},
}
@inproceedings{haefner2018cvpr,
title = {Fight ill-posedness with ill-posedness: Single-shot variational depth super-resolution from shading},
author = {B. Haefner and Y. Quéau and T. Möllenhoff and D. Cremers},
booktitle = {I{EEE}/{CVF} {C}onference on {C}omputer {V}ision and {P}attern {R}ecognition
(CVPR)},
year = {2018},
doi = {10.1109/CVPR.2018.00025},
titleurl = {haefner2018cvpr.pdf},
award = {Spotlight Presentation},
keywords = {rgb-d,reconstruction,3d-reconstruction,photometry,variational,super-resolution,photometricdepthsr},
}
@inproceedings{moellenhoff-iccv-2017,
title = {Sublabel-Accurate Discretization of Nonconvex Free-Discontinuity Problems},
author = {T. Möllenhoff and D. Cremers},
booktitle = {International Conference on Computer Vision (ICCV)},
year = {2017},
month = {October},
address = {Venice, Italy},
keywords = {convex-relaxation},
}
@inproceedings{moellenhoff-et-al-combinatorial-18,
author = {T. Möllenhoff and Z. Ye and T. Wu and D. Cremers},
title = {Combinatorial Preconditioners for Proximal Algorithms on Graphs},
booktitle = {International Conference on Artificial
Intelligence and Statistics (AISTATS)},
year = {2018},
titleurl = {moellenhoff-et-al-combinatorial-18.pdf},
}
@inproceedings{Frerix-et-al-18,
author = {T. Frerix and T. Möllenhoff and M. Moeller and D. Cremers},
title = {Proximal Backpropagation},
booktitle = {International Conference on Learning Representations (ICLR)},
primaryclass = {cs.LG},
year = {2018},
}
@article{laude2021lifting,
title = {Lifting the Convex Conjugate in Lagrangian Relaxations: {A} Tractable
Approach for Continuous Markov Random Fields},
author = {H Bauermeister and E Laude and T Möllenhoff and M Möller and D Cremers},
journal = {{SIAM} J. Imaging Sci.},
volume = {15},
number = {3},
pages = {1253--1281},
year = {2022},
keywords = {Markov random fields, moment relaxation, sum of squares, polynomial optimization, generalized conjugacy, optimal transport},
}
@inproceedings{moellenh-cvpr-19,
author = {T. Möllenhoff and D. Cremers},
title = {Lifting Vectorial Variational Problems: A Natural Formulation based on
Geometric Measure Theory and Discrete Exterior Calculus},
booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
year = {2019},
titleurl = {moellenh-cvpr-19.pdf},
award = {Oral Presentation},
}
@inproceedings{flatgan-icml-19,
author = {T. Möllenhoff and D. Cremers},
title = {Flat Metric Minimization with Applications in Generative Modeling},
booktitle = {International Conference on Machine Learning (ICML)},
primaryclass = {cs.LG},
year = {2019},
award = {Full Oral Presentation},
month = {6},
}
@inproceedings{moeller-et-al-19,
author = {M. Moeller and T. Möllenhoff and D. Cremers},
title = {Controlling Neural Networks via Energy Dissipation},
booktitle = {International Conference on Computer Vision (ICCV)},
year = {2019},
month = {10},
address = {Seoul, South Korea},
eprint = {1904.03081},
eprinttype = {arXiv},
eprintclass = {cs.CV},
}
@inproceedings{brechet2019,
title = {Informative GANs via Structured Regularization of Optimal Transport},
author = {P. Bréchet and T. Wu and T. Möllenhoff and D. Cremers},
booktitle = {{NeurIPS Workshop on Optimal Transport and Machine Learning}},
year = {2019},
eprint = {1912.02160},
eprinttype = {arXiv},
eprintclass = {cs.CV},
}
@inproceedings{ye2020optimization,
author = {Z. Ye and T. Möllenhoff and T. Wu and D. Cremers},
title = {Optimization of Graph Total Variation via Active-Set-based Combinatorial Reconditioning},
booktitle = {International Conference on Artificial
Intelligence and Statistics (AISTATS)},
year = {2020},
titleurl = {ye-et-al-combinatorial-20.pdf},
}
@inproceedings{ye2021gcpr,
author = {Z. Ye and B. Haefner and Y. Quéau and T. Möllenhoff and D. Cremers},
title = {Sublabel-Accurate Multilabeling Meets Product Label Spaces},
booktitle = {DAGM German Conference on Pattern Recognition (GCPR)},
year = {2021},
doi = {10.1007/978-3-030-92659-5_1},
%eprint = {},
%eprinttype = {arXiv},
%eprintclass = {cs.CV},
award = {Oral Presentation},
%titleurl = {},
keywords = {},
}
@article{ye2022ijcv,
author = {Z. Ye and B. Haefner and Y. Quéau and T. Möllenhoff and D. Cremers},
title = {A Cutting-Plane Method for Sublabel-Accurate Relaxation of Problems with Product Label Spaces},
journal = {International Journal of Computer Vision (IJCV)},
year = {2022},
doi = {10.1007/s11263-022-01704-7},
titleurl = {ye2022ijcv.pdf},
keywords = {},
}
@inproceedings{shen2024variational,
title = {Variational Learning is Effective for Large Deep Networks},
author = {Y Shen and N Daheim and B Cong and P Nickl and GM Marconi and C Bazan and R Yokota and I Gurevych and D Cremers and ME Khan and T Möllenhoff},
booktitle = {International Conference on Machine Learning (ICML)},
year = {2024},
award = {Spotlight},
eprint = {2402.17641},
eprinttype = {arXiv},
eprintclass = {cs.LG},
keywords = {deep learning},
}