ConTextTab: A Semantics-Aware Tabular In-Context Learner
Tabular in-context learning (ICL) has recently achieved state-of-the-art (SOTA) performance on several tabular prediction tasks. Previously restricted to cla...
Posts by Category
- publications 33
- conference 13
- cv 10
- journal 10
- workexperience 7
- software 4
- education 3
- theses 3
- dataset 3
- news 1
publications
Progressive Updates of Convolutional Neural Networks for Enhanced Reliability in Small Satellite Applications
Small satellites enable many important applications for both economic and scientific purposes. Many of these applications are inherently data-centric and rel...
A Compact Multispectral Light Field Camera Based on an Inkjet-printed Microlens Array and Color Filter Array
With emerging advanced optical sensing technologies and their wide-ranging applications, gathering comprehensive optical data from real-world scenes is becom...
Explainability and Interpretability in Electric Load Forecasting Using Machine Learning Techniques – A Review
Electric Load Forecasting (ELF) is the central instrument for planning and controlling demand response programs, electricity trading, and consumption optimiz...
Towards Tabular Foundation Models: Status Quo, Challenges, and Opportunities
This whitepaper presents an in-depth exploration of Tabular Foundation Models (TFMs), an emerging area in the broader context of deep learning and Foundation...
Scaling Experiments in Self-Supervised Cross-Table Representation Learning
To analyze the scaling potential of deep tabular representation learning models, we introduce a novel Transformer-based architecture specifically tailored to...
Curve Your Enthusiasm: Concurvity Regularization in Differentiable Generalized Additive Models
Generalized Additive Models (GAMs) have recently experienced a resurgence in popularity due to their interpretability, which arises from expressing the targe...
Curve Your Enthusiasm: Concurvity Regularization in Differentiable Generalized Additive Models
Generalized Additive Models (GAMs) have recently experienced a resurgence in popularity due to their interpretability, which arises from expressing the targe...
Filling the Gap: Fault-Tolerant Updates of On-Satellite Neural Networks Using Vector Quantization
The use of small, low-Earth-orbit satellites enables many novel Earth observation use cases due to their cost efficiency. To cope with the challenging commun...
Uncovering the Inner Workings of STEGO for Safe Unsupervised Semantic Segmentation
Self-supervised pre-training strategies have recently shown impressive results for training general-purpose feature extraction backbones in computer vision. ...
Interpretable Reinforcement Learning via Neural Additive Models for Inventory Management
The COVID-19 pandemic has highlighted the importance of supply chains and the role of digital management to react to dynamic changes in the environment. In ...
Fabrication of Microlens Arrays with High Quality and High Fill Factor by Inkjet Printing
Microlens arrays (MLAs) have a variety of applications in, e.g., display systems, projection optics, and sensor applications. They can be manufactured by va...
Reconstruction from Spatio-Spectrally Coded Multispectral Light Fields
In this thesis, spatio-spectrally coded multispectral light fields, as taken by a light field camera with a spectrally coded microlens array, are investigate...
A Highly Textured Real-World Multispectral Light Field Dataset
We provide a real-world multispectral light field dataset of highly textured scenes. The light fields were captured using a custom-built multispectral light ...
Spectral Reconstruction and Disparity from Spatio-Spectrally Coded Light Fields via Multi-Task Deep Learning
We present a novel method to reconstruct a spectral central view and its aligned disparity map from spatio-spectrally coded light fields. Since we do not rec...
Improving Light Efficiency in Multispectral Imaging via Complementary Notch Filters
We propose a novel multispectral imaging technique employing complementary notch filters instead of bandpass filters which are conventionally used in filter-...
Automated Quality Assessment of Inkjet-Printed Microlens Arrays
Recently, inkjet-printed microoptics, such as microlens arrays, have become popular in scientific research as well as industrial applications due to the fast...
Automated Quantitative Quality Assessment of Printed Microlens Arrays
We propose an automated evaluation pipeline uti-lizing both bright field light and confocal microscope imagesas well as multiple quality measures to quantita...
Signal-Adapted Analytic Wavelet Packets in Arbitrary Dimensions
The analytic wavelet packet transform, based on the dual-tree approach, represents a complex-valued extension of the wavelet packet transform. A generalizati...
A Multispectral Light Field Dataset and Framework for Light Field Deep Learning
Deep learning undoubtedly has had a huge impact on the computer vision community in recent years. In light field imaging, machine learning-based applications...
A Synthetic Multispectral Light Field Dataset for Light Field Deep Learning
Deep learning undoubtedly has had a huge impact on the computer vision community in recent years. In light field imaging, machine learning-based applications...
Microlens Array Grid Estimation, Light Field Decoding, and Calibration
We quantitatively investigate multiple algorithms for microlens array grid estimation for microlens array-based light field cameras. Explicitly taking into a...
Synthetic Whiteimages for the Lytro Illum Light Field Camera with Ground Truth Microlens Center Coordinates
We provide a dataset with synthetic white images for the Lytro Illum light field camera with precisely known microlens center coordinates. The dataset consis...
Reconstruction of Multispectral Images from Spectrally Coded Light Fields of Flat Scenes
We present a novel method to reconstruct multispectral images of flat objects from spectrally coded light fields as taken by an unfocused light field camera ...
A Simulation Framework for the Design and Evaluation of Computational Cameras
In the emerging field of computational imaging, rapid prototyping of new camera concepts becomes increasingly difficult since the signal processing is intert...
Algorithms for Microlens Center Detection
We investigate four algorithms for microlens center detection, two of which have not been previously discussed in the literature. Using a physical approach, ...
The Proca Field in Curved Spacetimes and its Zero Mass Limit
We investigate the classical and quantum Proca field (a massive vector potential) of mass $m > 0$ in arbitrary globally hyperbolic spacetimes and in the p...
Quantization of the Proca field in curved spacetimes – A study of mass dependence and the zero mass limit
In this thesis we investigate the Proca field in arbitrary globally hyperbolic curved spacetimes. We rigorously construct solutions to the classical Proca e...
Graphical expansion of the partition function for the supersymmetric non-linear σ-model in (1+0) D
In the present work, a graphical evolution of the fermionic part of the state sum of the supersymmetric nonlinear σ-model in (1 + 0) dimensions is presented....
conference
ConTextTab: A Semantics-Aware Tabular In-Context Learner
Tabular in-context learning (ICL) has recently achieved state-of-the-art (SOTA) performance on several tabular prediction tasks. Previously restricted to cla...
Scaling Experiments in Self-Supervised Cross-Table Representation Learning
To analyze the scaling potential of deep tabular representation learning models, we introduce a novel Transformer-based architecture specifically tailored to...
Curve Your Enthusiasm: Concurvity Regularization in Differentiable Generalized Additive Models
Generalized Additive Models (GAMs) have recently experienced a resurgence in popularity due to their interpretability, which arises from expressing the targe...
Curve Your Enthusiasm: Concurvity Regularization in Differentiable Generalized Additive Models
Generalized Additive Models (GAMs) have recently experienced a resurgence in popularity due to their interpretability, which arises from expressing the targe...
Filling the Gap: Fault-Tolerant Updates of On-Satellite Neural Networks Using Vector Quantization
The use of small, low-Earth-orbit satellites enables many novel Earth observation use cases due to their cost efficiency. To cope with the challenging commun...
Uncovering the Inner Workings of STEGO for Safe Unsupervised Semantic Segmentation
Self-supervised pre-training strategies have recently shown impressive results for training general-purpose feature extraction backbones in computer vision. ...
Interpretable Reinforcement Learning via Neural Additive Models for Inventory Management
The COVID-19 pandemic has highlighted the importance of supply chains and the role of digital management to react to dynamic changes in the environment. In ...
Spectral Reconstruction and Disparity from Spatio-Spectrally Coded Light Fields via Multi-Task Deep Learning
We present a novel method to reconstruct a spectral central view and its aligned disparity map from spatio-spectrally coded light fields. Since we do not rec...
Improving Light Efficiency in Multispectral Imaging via Complementary Notch Filters
We propose a novel multispectral imaging technique employing complementary notch filters instead of bandpass filters which are conventionally used in filter-...
Automated Quantitative Quality Assessment of Printed Microlens Arrays
We propose an automated evaluation pipeline uti-lizing both bright field light and confocal microscope imagesas well as multiple quality measures to quantita...
Signal-Adapted Analytic Wavelet Packets in Arbitrary Dimensions
The analytic wavelet packet transform, based on the dual-tree approach, represents a complex-valued extension of the wavelet packet transform. A generalizati...
A Simulation Framework for the Design and Evaluation of Computational Cameras
In the emerging field of computational imaging, rapid prototyping of new camera concepts becomes increasingly difficult since the signal processing is intert...
Algorithms for Microlens Center Detection
We investigate four algorithms for microlens center detection, two of which have not been previously discussed in the literature. Using a physical approach, ...
cv
journal
Progressive Updates of Convolutional Neural Networks for Enhanced Reliability in Small Satellite Applications
Small satellites enable many important applications for both economic and scientific purposes. Many of these applications are inherently data-centric and rel...
A Compact Multispectral Light Field Camera Based on an Inkjet-printed Microlens Array and Color Filter Array
With emerging advanced optical sensing technologies and their wide-ranging applications, gathering comprehensive optical data from real-world scenes is becom...
Explainability and Interpretability in Electric Load Forecasting Using Machine Learning Techniques – A Review
Electric Load Forecasting (ELF) is the central instrument for planning and controlling demand response programs, electricity trading, and consumption optimiz...
Towards Tabular Foundation Models: Status Quo, Challenges, and Opportunities
This whitepaper presents an in-depth exploration of Tabular Foundation Models (TFMs), an emerging area in the broader context of deep learning and Foundation...
Fabrication of Microlens Arrays with High Quality and High Fill Factor by Inkjet Printing
Microlens arrays (MLAs) have a variety of applications in, e.g., display systems, projection optics, and sensor applications. They can be manufactured by va...
Automated Quality Assessment of Inkjet-Printed Microlens Arrays
Recently, inkjet-printed microoptics, such as microlens arrays, have become popular in scientific research as well as industrial applications due to the fast...
A Multispectral Light Field Dataset and Framework for Light Field Deep Learning
Deep learning undoubtedly has had a huge impact on the computer vision community in recent years. In light field imaging, machine learning-based applications...
Microlens Array Grid Estimation, Light Field Decoding, and Calibration
We quantitatively investigate multiple algorithms for microlens array grid estimation for microlens array-based light field cameras. Explicitly taking into a...
Reconstruction of Multispectral Images from Spectrally Coded Light Fields of Flat Scenes
We present a novel method to reconstruct multispectral images of flat objects from spectrally coded light fields as taken by an unfocused light field camera ...
The Proca Field in Curved Spacetimes and its Zero Mass Limit
We investigate the classical and quantum Proca field (a massive vector potential) of mass $m > 0$ in arbitrary globally hyperbolic spacetimes and in the p...
workexperience
software
education
theses
Reconstruction from Spatio-Spectrally Coded Multispectral Light Fields
In this thesis, spatio-spectrally coded multispectral light fields, as taken by a light field camera with a spectrally coded microlens array, are investigate...
Quantization of the Proca field in curved spacetimes – A study of mass dependence and the zero mass limit
In this thesis we investigate the Proca field in arbitrary globally hyperbolic curved spacetimes. We rigorously construct solutions to the classical Proca e...
Graphical expansion of the partition function for the supersymmetric non-linear σ-model in (1+0) D
In the present work, a graphical evolution of the fermionic part of the state sum of the supersymmetric nonlinear σ-model in (1 + 0) dimensions is presented....
dataset
A Highly Textured Real-World Multispectral Light Field Dataset
We provide a real-world multispectral light field dataset of highly textured scenes. The light fields were captured using a custom-built multispectral light ...
A Synthetic Multispectral Light Field Dataset for Light Field Deep Learning
Deep learning undoubtedly has had a huge impact on the computer vision community in recent years. In light field imaging, machine learning-based applications...
Synthetic Whiteimages for the Lytro Illum Light Field Camera with Ground Truth Microlens Center Coordinates
We provide a dataset with synthetic white images for the Lytro Illum light field camera with precisely known microlens center coordinates. The dataset consis...
news
Welcome to my website!
Moin! I have finally managed to put together a website using GitHub pages and the minimal-mistakes Jekyll template.