Header logo is


2019


Towards Geometric Understanding of Motion
Towards Geometric Understanding of Motion

Ranjan, A.

University of Tübingen, December 2019 (phdthesis)

Abstract

The motion of the world is inherently dependent on the spatial structure of the world and its geometry. Therefore, classical optical flow methods try to model this geometry to solve for the motion. However, recent deep learning methods take a completely different approach. They try to predict optical flow by learning from labelled data. Although deep networks have shown state-of-the-art performance on classification problems in computer vision, they have not been as effective in solving optical flow. The key reason is that deep learning methods do not explicitly model the structure of the world in a neural network, and instead expect the network to learn about the structure from data. We hypothesize that it is difficult for a network to learn about motion without any constraint on the structure of the world. Therefore, we explore several approaches to explicitly model the geometry of the world and its spatial structure in deep neural networks.

The spatial structure in images can be captured by representing it at multiple scales. To represent multiple scales of images in deep neural nets, we introduce a Spatial Pyramid Network (SpyNet). Such a network can leverage global information for estimating large motions and local information for estimating small motions. We show that SpyNet significantly improves over previous optical flow networks while also being the smallest and fastest neural network for motion estimation. SPyNet achieves a 97% reduction in model parameters over previous methods and is more accurate.

The spatial structure of the world extends to people and their motion. Humans have a very well-defined structure, and this information is useful in estimating optical flow for humans. To leverage this information, we create a synthetic dataset for human optical flow using a statistical human body model and motion capture sequences. We use this dataset to train deep networks and see significant improvement in the ability of the networks to estimate human optical flow.

The structure and geometry of the world affects the motion. Therefore, learning about the structure of the scene together with the motion can benefit both problems. To facilitate this, we introduce Competitive Collaboration, where several neural networks are constrained by geometry and can jointly learn about structure and motion in the scene without any labels. To this end, we show that jointly learning single view depth prediction, camera motion, optical flow and motion segmentation using Competitive Collaboration achieves state-of-the-art results among unsupervised approaches.

Our findings provide support for our hypothesis that explicit constraints on structure and geometry of the world lead to better methods for motion estimation.

ps

PhD Thesis [BibTex]

2019


PhD Thesis [BibTex]


Semi-supervised learning, causality, and the conditional cluster assumption
Semi-supervised learning, causality, and the conditional cluster assumption

von Kügelgen, J., Mey, A., Loog, M., Schölkopf, B.

NeurIPS 2019 Workshop “Do the right thing”: machine learning and causal inference for improved decision making, December 2019 (poster)

ei

Poster PDF link (url) [BibTex]

Poster PDF link (url) [BibTex]


Optimal experimental design via Bayesian optimization: active causal structure learning for Gaussian process networks
Optimal experimental design via Bayesian optimization: active causal structure learning for Gaussian process networks

von Kügelgen, J., Rubenstein, P. K., Schölkopf, B., Weller, A.

NeurIPS 2019 Workshop “Do the right thing”: machine learning and causal inference for improved decision making, December 2019 (poster)

ei

arXiv Poster link (url) [BibTex]

arXiv Poster link (url) [BibTex]


no image
Robot Learning for Muscular Systems

Büchler, D.

Technical University Darmstadt, Germany, December 2019 (phdthesis)

ei

[BibTex]

[BibTex]


no image
Real Time Probabilistic Models for Robot Trajectories

Gomez-Gonzalez, S.

Technical University Darmstadt, Germany, December 2019 (phdthesis)

ei

[BibTex]

[BibTex]


no image
Reinforcement Learning for a Two-Robot Table Tennis Simulation

Li, G.

RWTH Aachen University, Germany, July 2019 (mastersthesis)

ei

[BibTex]

[BibTex]


no image
Demo Abstract: Fast Feedback Control and Coordination with Mode Changes for Wireless Cyber-Physical Systems

(Best Demo Award)

Mager, F., Baumann, D., Jacob, R., Thiele, L., Trimpe, S., Zimmerling, M.

Proceedings of the 18th ACM/IEEE Conference on Information Processing in Sensor Networks (IPSN), pages: 340-341, 18th ACM/IEEE Conference on Information Processing in Sensor Networks (IPSN), April 2019 (poster)

ics

arXiv PDF DOI [BibTex]

arXiv PDF DOI [BibTex]


Fast and Resource-Efficient Control of Wireless Cyber-Physical Systems
Fast and Resource-Efficient Control of Wireless Cyber-Physical Systems

Baumann, D.

KTH Royal Institute of Technology, Stockholm, Febuary 2019 (phdthesis)

ics

PDF [BibTex]

PDF [BibTex]


no image
X-ray microscopic characterization of high-Tc-supercoductors using image processing

Bihler, M.

Universität Stuttgart, Stuttgart, 2019 (mastersthesis)

mms

[BibTex]


no image
Learning Transferable Representations

Rojas-Carulla, M.

University of Cambridge, UK, 2019 (phdthesis)

ei

[BibTex]

[BibTex]


no image
Sample-efficient deep reinforcement learning for continuous control

Gu, S.

University of Cambridge, UK, 2019 (phdthesis)

ei

[BibTex]


no image
Ferromagnetic colloids in liquid crystal solvents

Zarubin, G.

Universität Stuttgart, Stuttgart, 2019 (phdthesis)

icm

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
Fluctuating interface with a pinning potential

Pranjić, Daniel

Universität Stuttgart, Stuttgart, 2019 (mastersthesis)

icm

[BibTex]

[BibTex]


no image
Spatial Filtering based on Riemannian Manifold for Brain-Computer Interfacing

Xu, J.

Technical University of Munich, Germany, 2019 (mastersthesis)

ei

[BibTex]

[BibTex]


no image
Perception of temporal dependencies in autoregressive motion

Meding, K., Schölkopf, B., Wichmann, F. A.

European Conference on Visual Perception (ECVP), 2019 (poster)

ei

[BibTex]

[BibTex]


no image
Novel X-ray lenses for direct and coherent imaging

Sanli, U. T.

Universität Stuttgart, Stuttgart, 2019 (phdthesis)

mms

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
Quantification of tumor heterogeneity using PET/MRI and machine learning

Katiyar, P.

Eberhard Karls Universität Tübingen, Germany, 2019 (phdthesis)

ei

[BibTex]

[BibTex]


no image
Controlling pattern formation in the confined Schnakenberg model

Beyer, David Bernhard

Universität Stuttgart, Stuttgart, 2019 (mastersthesis)

icm

[BibTex]

[BibTex]


no image
Phenomenal Causality and Sensory Realism

Bruijns, S. A., Meding, K., Schölkopf, B., Wichmann, F. A.

European Conference on Visual Perception (ECVP), 2019 (poster)

ei

[BibTex]

[BibTex]


no image
Interfaces in fluids of ionic liquid crystals

Bartsch, H.

Universität Stuttgart, Stuttgart, 2019 (phdthesis)

icm

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
Actively Learning Dynamical Systems with Gaussian Processes

Buisson-Fenet, M.

Mines ParisTech, PSL University, 2019 (mastersthesis)

Abstract
Predicting the behavior of complex systems is of great importance in many fields such as engineering, economics or meteorology. The evolution of such systems often follows a certain structure, which can be induced, for example from the laws of physics or of market forces. Mathematically, this structure is often captured by differential equations. The internal functional dependencies, however, are usually unknown. Hence, using machine learning approaches that recreate this structure directly from data is a promising alternative to designing physics-based models. In particular, for high dimensional systems with nonlinear effects, this can be a challenging task. Learning dynamical systems is different from the classical machine learning tasks, such as image processing, and necessitates different tools. Indeed, dynamical systems can be actuated, often by applying torques or voltages. Hence, the user has a power of decision over the system, and can drive it to certain states by going through the dynamics. Actuating this system generates data, from which a machine learning model of the dynamics can be trained. However, gathering informative data that is representative of the whole state space remains a challenging task. The question of active learning then becomes important: which control inputs should be chosen by the user so that the data generated during an experiment is informative, and enables efficient training of the dynamics model? In this context, Gaussian processes can be a useful framework for approximating system dynamics. Indeed, they perform well on small and medium sized data sets, as opposed to most other machine learning frameworks. This is particularly important considering data is often costly to generate and process, most of all when producing it involves actuating a complex physical system. Gaussian processes also yield a notion of uncertainty, which indicates how sure the model is about its predictions. In this work, we investigate in a principled way how to actively learn dynamical systems, by selecting control inputs that generate informative data. We model the system dynamics by a Gaussian process, and use information-theoretic criteria to identify control trajectories that maximize the information gain. Thus, the input space can be explored efficiently, leading to a data-efficient training of the model. We propose several methods, investigate their theoretical properties and compare them extensively in a numerical benchmark. The final method proves to be efficient at generating informative data. Thus, it yields the lowest prediction error with the same amount of samples on most benchmark systems. We propose several variants of this method, allowing the user to trade off computations with prediction accuracy, and show it is versatile enough to take additional objectives into account.

ics

[BibTex]

[BibTex]

2016


Non-parametric Models for Structured Data and Applications to Human Bodies and Natural Scenes
Non-parametric Models for Structured Data and Applications to Human Bodies and Natural Scenes

Lehrmann, A.

ETH Zurich, July 2016 (phdthesis)

Abstract
The purpose of this thesis is the study of non-parametric models for structured data and their fields of application in computer vision. We aim at the development of context-sensitive architectures which are both expressive and efficient. Our focus is on directed graphical models, in particular Bayesian networks, where we combine the flexibility of non-parametric local distributions with the efficiency of a global topology with bounded treewidth. A bound on the treewidth is obtained by either constraining the maximum indegree of the underlying graph structure or by introducing determinism. The non-parametric distributions in the nodes of the graph are given by decision trees or kernel density estimators. The information flow implied by specific network topologies, especially the resultant (conditional) independencies, allows for a natural integration and control of contextual information. We distinguish between three different types of context: static, dynamic, and semantic. In four different approaches we propose models which exhibit varying combinations of these contextual properties and allow modeling of structured data in space, time, and hierarchies derived thereof. The generative character of the presented models enables a direct synthesis of plausible hypotheses. Extensive experiments validate the developed models in two application scenarios which are of particular interest in computer vision: human bodies and natural scenes. In the practical sections of this work we discuss both areas from different angles and show applications of our models to human pose, motion, and segmentation as well as object categorization and localization. Here, we benefit from the availability of modern datasets of unprecedented size and diversity. Comparisons to traditional approaches and state-of-the-art research on the basis of well-established evaluation criteria allows the objective assessment of our contributions.

ps

pdf [BibTex]


no image
Autofocusing-based correction of B0 fluctuation-induced ghosting

Loktyushin, A., Ehses, P., Schölkopf, B., Scheffler, K.

24th Annual Meeting and Exhibition of the International Society for Magnetic Resonance in Medicine (ISMRM), May 2016 (poster)

ei

link (url) [BibTex]

link (url) [BibTex]


no image
Distinct adaptation to abrupt and gradual torque perturbations with a multi-joint exoskeleton robot

Oh, Y., Sutanto, G., Mistry, M., Schweighofer, N., Schaal, S.

Abstracts of Neural Control of Movement Conference (NCM 2016), Montego Bay, Jamaica, April 2016 (poster)

am

[BibTex]

[BibTex]


no image
PGO wave-triggered functional MRI: mapping the networks underlying synaptic consolidation

Logothetis, N. K., Murayama, Y., Ramirez-Villegas, J. F., Besserve, M., Evrard, H.

47th Annual Meeting of the Society for Neuroscience (Neuroscience), 2016 (poster)

ei

[BibTex]

[BibTex]


no image
Diffusion im Zentrifugalpotential

Totikos, Vangelis

Universität Stuttgart, Stuttgart, 2016 (mastersthesis)

icm

[BibTex]

[BibTex]


{Statische und dynamische Magnetisierungseigenschaften nanoskaliger \"Uberstrukturen}
Statische und dynamische Magnetisierungseigenschaften nanoskaliger Überstrukturen

Gräfe, J.

Universität Stuttgart, Stuttgart (und Cuvillier Verlag, Göttingen), 2016 (phdthesis)

mms

[BibTex]

[BibTex]


no image
Electromagnetic radiation in complex environments: Many body systems and background medium

Müller, Boris

Universität Stuttgart, Stuttgart, 2016 (mastersthesis)

icm

[BibTex]

[BibTex]


no image
Statistical source separation of rhythmic LFP patterns during sharp wave ripples in the macaque hippocampus

Ramirez-Villegas, J. F., Logothetis, N. K., Besserve, M.

47th Annual Meeting of the Society for Neuroscience (Neuroscience), 2016 (poster)

ei

[BibTex]

[BibTex]


no image
Screening Rules for Convex Problems

Raj, A., Olbrich, J., Gärtner, B., Schölkopf, B., Jaggi, M.

2016 (unpublished) Submitted

ei

[BibTex]

[BibTex]


no image
Theory of enantiomer separation by external fields

Gehrmann, Christian

Universität Stuttgart, Stuttgart, 2016 (mastersthesis)

icm

[BibTex]

[BibTex]


no image
Hippocampal neural events predict ongoing brain-wide BOLD activity

Besserve, M., Logothetis, N. K.

47th Annual Meeting of the Society for Neuroscience (Neuroscience), 2016 (poster)

ei

[BibTex]

[BibTex]


no image
General properties of ionic complex fluids

Bier, M.

Universität Stuttgart, Stuttgart, 2016 (phdthesis)

icm

[BibTex]

[BibTex]


no image
Wedge wetting by an electrolyte solution

Mu\ssotter, M.

Universität Stuttgart, Stuttgart, 2016 (mastersthesis)

icm

[BibTex]

[BibTex]


no image
Gepinnte Bahnmomente in magnetischen Heterostrukturen

Audehm, P.

Universität Stuttgart, Stuttgart (und Cuvillier Verlag, Göttingen), 2016 (phdthesis)

mms

[BibTex]

[BibTex]


no image
Austauschgekoppelte Moden in magnetischen Vortexstrukturen

Dieterle, G.

Universität Stuttgart, Stuttgart, 2016 (phdthesis)

mms

[BibTex]

[BibTex]


no image
Density matrix calculations for the ultrafast demagnetization after femtosecond laser pulses

Weng, Weikai

Universität Stuttgart, Stuttgart, 2016 (mastersthesis)

mms

[BibTex]

[BibTex]


no image
Deep Learning for Diabetic Retinopathy Diagnostics

Balles, Lukas

Heidelberg University, 2016 (mastersthesis)

[BibTex]

[BibTex]


no image
Helium und Hydrogen Isotope Adsorption and Separation in Metal-Organic Frameworks

Zaiser, Ingrid

Universität Stuttgart, Stuttgart (und Cuvillier Verlag, Göttingen), 2016 (phdthesis)

mms

[BibTex]

[BibTex]

2009


no image
Clinical PET/MRI-System and Its Applications with MRI Based Attenuation Correction

Kolb, A., Hofmann, M., Sossi, V., Wehrl, H., Sauter, A., Schmid, A., Schlemmer, H., Claussen, C., Pichler, B.

IEEE Nuclear Science Symposium and Medical Imaging Conference (NSS/MIC 2009), 2009, pages: 1, October 2009 (poster)

Abstract
Clinical PET/MRI is an emerging new hybrid imaging modality. In addition to provide an unique possibility for multifunctional imaging with temporally and spatially matched data, it also provides anatomical information that can also be used for attenuation correction with no radiation exposure to the subjects. A plus of combined compared to sequential PET and MR imaging is the reduction of total scan time. Here we present our initial experience with a hybrid brain PET/MRI system. Due to the ethical approval patient scans could only be performed after a diagnostic PET/CT. We estimate that in approximately 50% of the cases PET/MRI was of superior diagnostic value compared to PET/CT and was able to provide additional information, such as DTI, spectroscopy and Time Of Flight (TOF) angiography. Here we present 3 patient cases in oncology, a retropharyngeal carcinoma in neurooncology, a relapsing meningioma and in neurology a pharyngeal carcinoma in addition to an infraction of the right hemisphere. For quantitative PET imaging attenuation correction is obligatory. In current PET/MRI setup we used our MRI based atlas method for calculating the mu-map for attenuation correction. MR-based attenuation correction accuracy was quantitatively compared to CT-based PET attenuation correction. Extensive studies to assess potential mutual interferences between PET and MR imaging modalities as well as NEMA measurements have been performed. The first patient studies as well as the phantom tests clearly demonstrated the overall good imaging performance of this first human PET/MRI system. Ongoing work concentrates on advanced normalization and reconstruction methods incorporating count-rate based algorithms.

ei

Web [BibTex]

2009


Web [BibTex]