Search Results for author: Stefan Harmeling

Found 37 papers, 17 papers with code

How Will I Argue? A Dataset for Evaluating Recommender Systems for Argumentations

1 code implementation SIGDIAL (ACL) 2021 Markus Brenneis, Maike Behrendt, Stefan Harmeling

Exchanging arguments is an important part in communication, but we are often flooded with lots of arguments for different positions or are captured in filter bubbles.

Recommendation Systems

SQBC: Active Learning using LLM-Generated Synthetic Data for Stance Detection in Online Political Discussions

no code implementations11 Apr 2024 Stefan Sylvius Wagner, Maike Behrendt, Marc Ziegele, Stefan Harmeling

In this work, we present two different ways to leverage LLM-generated synthetic data to train and improve stance detection agents for online political discussions: first, we show that augmenting a small fine-tuning dataset with synthetic data can improve the performance of the stance detection model.

Active Learning Stance Detection

AQuA -- Combining Experts' and Non-Experts' Views To Assess Deliberation Quality in Online Discussions Using LLMs

1 code implementation3 Apr 2024 Maike Behrendt, Stefan Sylvius Wagner, Marc Ziegele, Lena Wilms, Anke Stoll, Dominique Heinbach, Stefan Harmeling

In this work, we introduce AQuA, an additive score that calculates a unified deliberative quality score from multiple indices for each discussion post.

Just Cluster It: An Approach for Exploration in High-Dimensions using Clustering and Pre-Trained Representations

no code implementations5 Feb 2024 Stefan Sylvius Wagner, Stefan Harmeling

In this paper we adopt a representation-centric perspective on exploration in reinforcement learning, viewing exploration fundamentally as a density estimation problem.

Clustering Density Estimation

Cyclophobic Reinforcement Learning

no code implementations30 Aug 2023 Stefan Sylvius Wagner, Peter Arndt, Jan Robine, Stefan Harmeling

In environments with sparse rewards, finding a good inductive bias for exploration is crucial to the agent's success.

Inductive Bias reinforcement-learning

Uncertainty-Aware Contour Proposal Networks for Cell Segmentation in Multi-Modality High-Resolution Microscopy Images

1 code implementation NeurIPS CellSeg 2022 2022 Eric Upschulte, Stefan Harmeling, Katrin Amunts, Timo Dickscheid

In the context of the NeurIPS 22 Cell Segmentation Challenge, the proposed solution is shown to generalize well in a multi-modality setting, while respecting domain-specific requirements such as focusing on specific cell types.

Cell Segmentation Instance Segmentation +2

Learning Causal Graphs in Manufacturing Domains using Structural Equation Models

no code implementations26 Oct 2022 Maximilian Kertel, Stefan Harmeling, Markus Pauly

Many production processes are characterized by numerous and complex cause-and-effect relationships.

Blindly Deconvolving Super-noisy Blurry Image Sequences

no code implementations1 Oct 2022 Leonid Kostrykin, Stefan Harmeling

In this paper, we consider multi-frame blind deconvolution (MFBD), where image blur is described by the convolution of an unobservable, undeteriorated image and an unknown filter, and the objective is to recover the undeteriorated image from a sequence of its blurry and noisy observations.

Optimizing Intermediate Representations of Generative Models for Phase Retrieval

1 code implementation31 May 2022 Tobias Uelwer, Sebastian Konietzny, Stefan Harmeling

With extensive experiments on the Fourier phase retrieval problem and thorough ablation studies, we can show the benefits of our modified ILO and the new initialization schemes.


Deblurring Photographs of Characters Using Deep Neural Networks

1 code implementation30 May 2022 Thomas Germer, Tobias Uelwer, Stefan Harmeling

Our method consists of three steps: First, we estimate a warping transformation of the images to align the sharp images with the blurred ones.


A Closer Look at Reference Learning for Fourier Phase Retrieval

1 code implementation NeurIPS Workshop Deep_Invers 2021 Tobias Uelwer, Nick Rucks, Stefan Harmeling

In this work, we consider a modified version of the phase retrieval problem, which allows for a reference image to be added onto the image before the Fourier magnitudes are measured.


Learning to Plan via a Multi-Step Policy Regression Method

no code implementations18 Jun 2021 Stefan Wagner, Michael Janschek, Tobias Uelwer, Stefan Harmeling

We propose a new approach to increase inference performance in environments that require a specific sequence of actions in order to be solved.


Non-Iterative Phase Retrieval With Cascaded Neural Networks

no code implementations18 Jun 2021 Tobias Uelwer, Tobias Hoffmann, Stefan Harmeling

Fourier phase retrieval is the problem of reconstructing a signal given only the magnitude of its Fourier transformation.


Contour Proposal Networks for Biomedical Instance Segmentation

2 code implementations7 Apr 2021 Eric Upschulte, Stefan Harmeling, Katrin Amunts, Timo Dickscheid

We construct CPN models with different backbone networks, and apply them to instance segmentation of cells in datasets from different modalities.

Blood Cell Detection Cell Detection +7

2D histology meets 3D topology: Cytoarchitectonic brain mapping with Graph Neural Networks

no code implementations9 Mar 2021 Christian Schiffer, Stefan Harmeling, Katrin Amunts, Timo Dickscheid

By solving the brain mapping problem on this graph using graph neural networks, we obtain significantly improved classification results.

Descriptive General Classification +1

Contrastive Representation Learning for Whole Brain Cytoarchitectonic Mapping in Histological Human Brain Sections

no code implementations25 Nov 2020 Christian Schiffer, Katrin Amunts, Stefan Harmeling, Timo Dickscheid

Cytoarchitectonic maps provide microstructural reference parcellations of the brain, describing its organization in terms of the spatial arrangement of neuronal cell bodies as measured from histological tissue sections.

Contrastive Learning General Classification +2

Convolutional Neural Networks for cytoarchitectonic brain mapping at large scale

no code implementations25 Nov 2020 Christian Schiffer, Hannah Spitzer, Kai Kiwitz, Nina Unger, Konrad Wagstyl, Alan C. Evans, Stefan Harmeling, Katrin Amunts, Timo Dickscheid

Here we present a new workflow for mapping cytoarchitectonic areas in large series of cell-body stained histological sections of human postmortem brains.

3D Reconstruction

Fast Multi-Level Foreground Estimation

1 code implementation26 Jun 2020 Thomas Germer, Tobias Uelwer, Stefan Conrad, Stefan Harmeling

Alpha matting aims to estimate the translucency of an object in a given image.

Image Matting

PyMatting: A Python Library for Alpha Matting

1 code implementation25 Mar 2020 Thomas Germer, Tobias Uelwer, Stefan Conrad, Stefan Harmeling

Alpha matting describes the problem of separating the objects in the foreground from the background of an image given only a rough sketch.

Image Matting

Phase Retrieval Using Conditional Generative Adversarial Networks

1 code implementation10 Dec 2019 Tobias Uelwer, Alexander Oberstraß, Stefan Harmeling

In this paper, we propose the application of conditional generative adversarial networks to solve various phase retrieval problems.


On the Vulnerability of Capsule Networks to Adversarial Attacks

1 code implementation9 Jun 2019 Felix Michels, Tobias Uelwer, Eric Upschulte, Stefan Harmeling

This paper extensively evaluates the vulnerability of capsule networks to different adversarial attacks.

Modular Block-diagonal Curvature Approximations for Feedforward Architectures

1 code implementation5 Feb 2019 Felix Dangel, Stefan Harmeling, Philipp Hennig

We propose a modular extension of backpropagation for the computation of block-diagonal approximations to various curvature matrices of the training objective (in particular, the Hessian, generalized Gauss-Newton, and positive-curvature Hessian).

BIG-bench Machine Learning

Improving Cytoarchitectonic Segmentation of Human Brain Areas with Self-supervised Siamese Networks

no code implementations13 Jun 2018 Hannah Spitzer, Kai Kiwitz, Katrin Amunts, Stefan Harmeling, Timo Dickscheid

We show that the self-supervised model has implicitly learned to distinguish several cortical brain areas -- a strong indicator that the proposed auxiliary task is appropriate for cytoarchitectonic mapping.

Parcellation of Visual Cortex on high-resolution histological Brain Sections using Convolutional Neural Networks

no code implementations30 May 2017 Hannah Spitzer, Katrin Amunts, Stefan Harmeling, Timo Dickscheid

Its high resolution allows the study of laminar and columnar patterns of cell distributions, which build an important basis for the simulation of cortical areas and networks.

Attribute-Based Classification for Zero-Shot Visual Object Categorization

no code implementations IEEE Transactions on Pattern Analysis and Machine Intelligence 2013 Christoph H. Lampert, Hannes Nickisch, Stefan Harmeling

To tackle the problem, we introduce attribute-based classification: Objects are identified based on a high-level description that is phrased in terms of semantic attributes, such as the object’s color or shape.

Attribute Classification +4

Space-Variant Single-Image Blind Deconvolution for Removing Camera Shake

no code implementations NeurIPS 2010 Stefan Harmeling, Hirsch Michael, Bernhard Schölkopf

Modelling camera shake as a space-invariant convolution simplifies the problem of removing camera shake, but often insufficiently models actual motion blur such as those due to camera rotation and movements outside the sensor plane or when objects in the scene have different distances to the camera.

How to Explain Individual Classification Decisions

no code implementations6 Dec 2009 David Baehrens, Timon Schroeter, Stefan Harmeling, Motoaki Kawanabe, Katja Hansen, Klaus-Robert Mueller

After building a classifier with modern tools of machine learning we typically have a black box at hand that is able to predict well for unseen data.

BIG-bench Machine Learning Classification +1

Cannot find the paper you are looking for? You can Submit a new open access paper.