Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Michael Moeller

What Doesn't Kill You Makes You Robust(er): Adversarial Training against Poisons and Backdoors


Feb 26, 2021
Jonas Geiping, Liam Fowl, Gowthami Somepalli, Micah Goldblum, Michael Moeller, Tom Goldstein

* 17 pages, 14 figures 

  Access Paper or Ask Questions

Witches' Brew: Industrial Scale Data Poisoning via Gradient Matching


Sep 04, 2020
Jonas Geiping, Liam Fowl, W. Ronny Huang, Wojciech Czaja, Gavin Taylor, Michael Moeller, Tom Goldstein

* First two authors contributed equally. Last two authors contributed equally. 21 pages, 11 figures 

  Access Paper or Ask Questions

Exploiting the Logits: Joint Sign Language Recognition and Spell-Correction


Jul 01, 2020
Christina Runkel, Stefan Dorenkamp, Hartmut Bauermeister, Michael Moeller

* First two authors contributed equally. Accepted at ICPR 2020 

  Access Paper or Ask Questions

A Simple Domain Shifting Networkfor Generating Low Quality Images


Jun 30, 2020
Guruprasad Hegde, Avinash Nittur Ramesh, Kanchana Vaishnavi Gandikota, Roman Obermaisser, Michael Moeller

* accepted ICPR 2020 

  Access Paper or Ask Questions

Generative Models for Generic Light Field Reconstruction


May 13, 2020
Paramanand Chandramouli, Kanchana Vaishnavi Gandikota, Andreas Goerlitz, Andreas Kolb, Michael Moeller


  Access Paper or Ask Questions

Fast Convex Relaxations using Graph Discretizations


Apr 23, 2020
Jonas Geiping, Fjedor Gaede, Hartmut Bauermeister, Michael Moeller

* 19 pages, 10 figures 

  Access Paper or Ask Questions

Inverting Gradients -- How easy is it to break privacy in federated learning?


Mar 31, 2020
Jonas Geiping, Hartmut Bauermeister, Hannah Dröge, Michael Moeller

* 26 pages, 17 figures. The first three authors contributed equally 

  Access Paper or Ask Questions

Truth or Backpropaganda? An Empirical Investigation of Deep Learning Theory


Oct 01, 2019
Micah Goldblum, Jonas Geiping, Avi Schwarzschild, Michael Moeller, Tom Goldstein

* 16 pages, 5 figures. First two authors contributed equally 

  Access Paper or Ask Questions

Parametric Majorization for Data-Driven Energy Minimization Methods


Aug 17, 2019
Jonas Geiping, Michael Moeller

* 16 pages, 5 figures, accepted for ICCV 2019 

  Access Paper or Ask Questions

Controlling Neural Networks via Energy Dissipation


Apr 05, 2019
Michael Moeller, Thomas Möllenhoff, Daniel Cremers


  Access Paper or Ask Questions

Composite Optimization by Nonconvex Majorization-Minimization


Sep 03, 2018
Jonas Geiping, Michael Moeller

* 38 pages, 12 figures, accepted for publication in SIIMS 

  Access Paper or Ask Questions

DS*: Tighter Lifting-Free Convex Relaxations for Quadratic Matching Problems


Jul 31, 2018
Florian Bernard, Christian Theobalt, Michael Moeller

* Published at CVPR 2018 

  Access Paper or Ask Questions

Convolutional Simplex Projection Network (CSPN) for Weakly Supervised Semantic Segmentation


Jul 24, 2018
Rania Briq, Michael Moeller, Juergen Gall

* BMVC 2018 

  Access Paper or Ask Questions

Are good local minima wide in sparse recovery?


Jun 21, 2018
Michael Moeller, Otmar Loffeld, Juergen Gall, Felix Krahmer


  Access Paper or Ask Questions

Lifting Layers: Analysis and Applications


Mar 23, 2018
Peter Ochs, Tim Meinhardt, Laura Leal-Taixe, Michael Moeller


  Access Paper or Ask Questions

Proximal Backpropagation


Feb 20, 2018
Thomas Frerix, Thomas Möllenhoff, Michael Moeller, Daniel Cremers

* Published as a conference paper at ICLR 2018 

  Access Paper or Ask Questions

Multiframe Motion Coupling for Video Super Resolution


Dec 04, 2017
Jonas Geiping, Hendrik Dirks, Daniel Cremers, Michael Moeller


  Access Paper or Ask Questions

Learning Proximal Operators: Using Denoising Networks for Regularizing Inverse Imaging Problems


Aug 30, 2017
Tim Meinhardt, Michael Moeller, Caner Hazirbas, Daniel Cremers


  Access Paper or Ask Questions

Sublabel-Accurate Convex Relaxation of Vectorial Multilabel Energies


Oct 10, 2016
Emanuel Laude, Thomas Möllenhoff, Michael Moeller, Jan Lellmann, Daniel Cremers


  Access Paper or Ask Questions

Sublabel-Accurate Relaxation of Nonconvex Energies


Dec 04, 2015
Thomas Möllenhoff, Emanuel Laude, Michael Moeller, Jan Lellmann, Daniel Cremers


  Access Paper or Ask Questions

Nonlinear Spectral Analysis via One-homogeneous Functionals - Overview and Future Prospects


Oct 05, 2015
Guy Gilboa, Michael Moeller, Martin Burger


  Access Paper or Ask Questions

Collaborative Total Variation: A General Framework for Vectorial TV Models


Aug 06, 2015
Joan Duran, Michael Moeller, Catalina Sbert, Daniel Cremers

* SIAM Journal on Imaging Sciences, vol. 9(1), pp. 116-151, 2016 

  Access Paper or Ask Questions

Point-wise Map Recovery and Refinement from Functional Correspondence


Jun 18, 2015
Emanuele RodolĂ , Michael Moeller, Daniel Cremers


  Access Paper or Ask Questions

Variational Depth from Focus Reconstruction


Nov 05, 2014
Michael Moeller, Martin Benning, Carola Schönlieb, Daniel Cremers


  Access Paper or Ask Questions

The Primal-Dual Hybrid Gradient Method for Semiconvex Splittings


Jul 07, 2014
Thomas Möllenhoff, Evgeny Strekalovskiy, Michael Moeller, Daniel Cremers


  Access Paper or Ask Questions

A Framework for Automated Cell Tracking in Phase Contrast Microscopic Videos based on Normal Velocities


Mar 27, 2012
Michael Moeller, Martin Burger, Peter Dieterich, Albrecht Schwab


  Access Paper or Ask Questions