# Differences

This shows you the differences between two versions of the page.

Both sides previous revision Previous revision Next revision | Previous revision | ||

research [2017/11/01 22:14] ipa [Geometric Low-Level Variational Image Analysis on Metric Measure Spaces] |
research [2019/10/24 11:52] (current) ipa [Variational Image Analysis on Manifolds and Metric Measure Spaces] |
||
---|---|---|---|

Line 1: | Line 1: | ||

====== Research ====== | ====== Research ====== | ||

- | ===== Geometric Low-Level Variational Image Analysis on Metric Measure Spaces ===== | + | ===== Variational Image Analysis on Manifolds and Metric Measure Spaces ===== |

- | We exploit basic statistical manifolds to devise variational models of low-level image analysis that exhibit favourable properties in comparison to established convex and non-convex models: smoothness, probabilistic interpretation, efficiently converging parallel and sparse Riemannian numerical updates that scale up to large problem sizes. The current focus is on the assignment manifold and image labeling, and on learning from image assignments in large-scale unsupervised scenarios, within the mathematical frameworks of information geometry and regularised optimal transport. | + | **Scope.** We exploit basic statistical manifolds to devise variational models of low-level image analysis that exhibit favourable properties in comparison to established convex and non-convex models: smoothness, probabilistic interpretation, efficiently converging parallel and sparse Riemannian numerical updates that scale up to large problem sizes. |

- | **Researchers**: Freddie Aström, Ruben Garske, Judit Recknagel, Fabrizio Savarino, Christoph Schnörr, Alexander Zeilmann | + | The current focus is on the **//assignment manifold//** and image labeling, and on learning from image assignments in large-scale unsupervised scenarios, within the mathematical frameworks of information geometry and regularised optimal transport. A novel smooth dynamical system evolving on a statistical manifold, called **//assignment flow//**, forms the basis of our work. |

- | We applied our approach to solve in a novel way the MAP labeling problem based on a given graphical model by smoothly combining a geometric reformulation of the local polytope relaxation with rounding to an integral solution. A key ingredient are local `Wasserstein messages' that couple local assignment measures along edges. | + | **Mathematical aspects.** The assignment flow evolves non-locally for any data given on a graph. Geometric and variational aspects, extensions to continuous domains, scale separation and models of knowledge representation across the scales are investigated. |

- | * [[https://arxiv.org/abs/1710.01493|preprint, arXiv:1710.01493, 2017]] | + | A preliminary extension from graphs to the continuous domain in the `zero-scale limit' (local interaction only) reveals the interplay between the underlying geometry and variational aspects. |

+ | * [[https://arxiv.org/abs/1910.07287|Continuous-Domain Assignment Flow, preprint arXiv:1910.07287]]. | ||

+ | A a more classical //additive// variational reformulation provides a smooth geometric version of the continuous cut approach. | ||

+ | * [[https://ipa.math.uni-heidelberg.de/dokuwiki/Papers/Savarino2019aa.pdf|A Variational Perspective on the Assignment Flow, SSVM 2019]]. | ||

- | Kick-off paper that introduces the basic approach: | + | **Parameter learning.** We study how weights for geometric diffusion that parametrize the adaptivity of the assignment flow can be learned from data. Symplectic integration ensures the commutativity of discretisation and optimisation operations. Results reveal the steerability of the assignment flow and its potential for pattern //formation//. |

+ | * [[https://arxiv.org/abs/1910.09976|Learning Adaptive Regularization for Image Labeling Using Geometric Assignment, preprint arXiv:1910.09976]] | ||

+ | * [[https://ipa.math.uni-heidelberg.de/dokuwiki/Papers/Huhnerbein2019aa.pdf|Conference version, SSVM 2019]]. | ||

- | * [[https://link.springer.com/article/10.1007/s10851-016-0702-4|J. Math. Imag. Vision, 2017]] | + | **Unsupervised label learning.** Our recent work concerns the emergence of labels in a completely unsupervised way by data //self//-assignment. The resulting unsupervised assignment flow has connections to low-rank matrix factorisation and discrete optimal mass transport that are explored in our current work. |

- | * [[https://www.readcube.com/articles/10.1007/s10851-016-0702-4?author_access_token=qTJknl5fUiTP-FjpTKUBO_e4RwlQNchNByi7wbcMAY6Xsf53Ss0CTbPqiHjWrFr9KxurTkJxDnblRwd66rV9vVhzVeITjqSsDSC8NWZFxg9y-pWgHhjix00mggjora7T-qHFcXzGInobFGxuIfcnEA%3D%3D|Link to online PDF]] | + | * [[https://ipa.math.uni-heidelberg.de/dokuwiki/Papers/Zisler2019aa.pdf|Unsupervised Labeling by Geometric and Spatially Regularized Self-Assignment, SSVM 2019]]. |

+ | | ||

+ | We extended the assignment flow to //unsupervised// scenarios, where label evolution on a feature manifold is simultaneously performed together with label assignment to given data. The following papers introduce the corresponding //unsupervised assignment flow//. | ||

+ | * [[https://ipa.math.uni-heidelberg.de/dokuwiki/Papers/Zern2019aa.pdf|Unsupervised Assignment Flow: Label Learning on Feature Manifolds by Spatially Regularized Geometric Assignment, preprint arXiv:1904.10863]] | ||

+ | * [[https://ipa.math.uni-heidelberg.de/dokuwiki/Papers/gcpr2018.pdf|Unsupervised Label Learning on Manifolds by Spatially Regularized Geometric Assignment, GCPR 2018]]. | ||

+ | | ||

+ | **Geometric numerical integration.** We conducted a comprehensive study of //geometric integration// techniques, including automatic step size adaption, for numerically computing the assignment flow in a stable, efficient and parameter-free way. | ||

+ | * [[https://iopscience.iop.org/article/10.1088/1361-6420/ab2772|Geometric Numerical Integration of the Assignment Flow, Inverse Problems, 2019]] | ||

+ | * [[https://ipa.math.uni-heidelberg.de/dokuwiki/Papers/Zeilmann2018aa.pdf|preprint: arXiv:1810.06970]] | ||

+ | | ||

+ | **Evaluation of discrete graphical models.** We applied our approach to solve in a novel way the //MAP labeling problem// based on a given graphical model by smoothly combining a geometric reformulation of the local polytope relaxation with rounding to an integral solution. A key ingredient are local `//Wasserstein messages//' that couple local assignment measures along edges. | ||

+ | | ||

+ | * [[https://epubs.siam.org/doi/abs/10.1137/17M1150669|Image Labeling Based on Graphical Models Using Wasserstein Messages and Geometric Assignment, SIAM J. on Imaging Science 11/2 (2018) 1317--1362]] | ||

+ | | ||

+ | **Kick-off paper** that introduces the basic approach: | ||

+ | | ||

+ | * [[https://ipa.math.uni-heidelberg.de/dokuwiki/Papers/Astroem2017.pdf|Image Labeling by Assignment., J. Math. Imag. Vision 58/2 (2017) 211--238]] | ||

* [[http://www-rech.telecom-lille.fr/diff-cv2016/|Proceedings DIFF-CVML'16; Grenander best paper award]] | * [[http://www-rech.telecom-lille.fr/diff-cv2016/|Proceedings DIFF-CVML'16; Grenander best paper award]] | ||

* [[https://ipa.iwr.uni-heidelberg.de/dokuwiki/Papers/Astroem2016d.pdf|Proceedings ECCV'16]] | * [[https://ipa.iwr.uni-heidelberg.de/dokuwiki/Papers/Astroem2016d.pdf|Proceedings ECCV'16]] | ||

Line 26: | Line 47: | ||

[[research:hflow:start|Details]] | [[research:hflow:start|Details]] | ||

- | ===== Phase Transitions and Recovery of Cosparse Objects Through Limited Angle Tomography ===== | ||

- | |||

- | Sampling patterns as used in industrial tomographical set-ups with limited numbers of projections fall short of the common assumptions (e.g.~restricted isometry property) underlying compressed sensing. In this project, we investigate the relation between the number of sufficient tomographic projections and the co-/sparsity of volume functions for unique recovery of these functions from given projection data. We also investigate approaches to efficiently solve the corresponding large numerical optimization problem in the 3D case. | ||

- | |||

- | |||

- | **Researchers**: Andreea Denitiu, Stefania Petra, Christoph Schnörr | ||

- | |||

- | [[research:tomography:start|Details]] | ||

- | |||

- | ===== Segmentation of Thin Fiber Structures in 3D Tomographical Data ===== | ||

- | |||

- | Recognizing the microstructure of fiber reinforced polymers is a necessary prerequisite for inferring macroscopic material properties. This project aims to combine low-level image processing and stochastic models of fiber distributions in order to reliably segment fibers in noisy image data. A major aspect concerns variational methods for approximate inference in connection with set covering, Gibbs distributions and marked point processes. | ||

- | |||

- | **Researchers**: | ||

- | Peter Markowsky, Tabea Zuber, Gabriele Steidl (TU Kaiserslautern), Christoph Schnörr | ||

Line 50: | Line 56: | ||

Johannes Berger, Andreas Neufeld, Florian Becker, Frank Lenzen, Christoph Schnörr | Johannes Berger, Andreas Neufeld, Florian Becker, Frank Lenzen, Christoph Schnörr | ||

- | [[https://hciweb.iwr.uni-heidelberg.de/node/2385|Details]] | + | Details: [[https://ipa.iwr.uni-heidelberg.de/dokuwiki/Papers/Berger2015a.pdf|Paper]] |

===== Partial Optimality in MAP-MRF ===== | ===== Partial Optimality in MAP-MRF ===== | ||

Line 57: | Line 63: | ||

**Researchers**: Paul Swoboda, Bogdan Savchynskyy, Alexander Shekhovtsov, Jörg Hendrik Kappes, Christoph Schnörr\\ | **Researchers**: Paul Swoboda, Bogdan Savchynskyy, Alexander Shekhovtsov, Jörg Hendrik Kappes, Christoph Schnörr\\ | ||

Details: [[https://ipa.iwr.uni-heidelberg.de/dokuwiki/Papers/Swoboda2016.pdf|Paper]] | Details: [[https://ipa.iwr.uni-heidelberg.de/dokuwiki/Papers/Swoboda2016.pdf|Paper]] | ||

- | ===== Context Specific Independence and Graphical Models ===== | ||

- | |||

- | This projects focuses on the connections between the field of probabilistic graphical models and the family of models that are able to represent efficiently distributions in which Context Specific Independences (CSIs) appear (dependences that are not fixed but only happen given a certain "context" state). Such models include And/Or graphs, Arithmetic Circuits, Sum-Product Networks, and others. | ||

- | |||

- | These CSI models are more expressive than graphical models but they lack the compactness and the theoretical framework of the latter. By creating new connections between the two fields we aim to translate algorithms and methodologies from one to the other, thereby obtaining a compact representation of CSI enjoying the sound probabilistic framework of graphical models. | ||

- | |||

- | A long-term objective is to better understand the properties of | ||

- | deep learning architectures, in particular those with a probabilistic | ||

- | interpretation. | ||

- | |||

- | **Researchers**: Mattia Desana, Christoph Schnörr | ||