Margret Keuper

Orcid: 0000-0002-8437-7993

Affiliations:
  • Mannheim University, Germany
  • University of Siegen, Germany (former)
  • Max Planck Institute for Informatics, Saarbrücken, Germany (former)


According to our database1, Margret Keuper authored at least 100 papers between 2009 and 2024.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2024
Intra- & Extra-Source Exemplar-Based Style Synthesis for Improved Domain Generalization.
Int. J. Comput. Vis., February, 2024

As large as it gets - Studying Infinitely Large Convolutions via Neural Implicit Frequency Filters.
Trans. Mach. Learn. Res., 2024

Learning the essential in less than 2k additional weights - a simple approach to improve image classification stability under corruptions.
Trans. Mach. Learn. Res., 2024

FAIR-TAT: Improving Model Fairness Using Targeted Adversarial Training.
CoRR, 2024

How Do Training Methods Influence the Utilization of Vision Models?
CoRR, 2024

Balancing Diversity and Risk in LLM Sampling: How to Select Your Method and Parameter for Open-Ended Text Generation.
CoRR, 2024

Domain-Aware Fine-Tuning of Foundation Models.
CoRR, 2024

Beware of Aliases - Signal Preservation is Crucial for Robust Image Restoration.
CoRR, 2024

VSTAR: Generative Temporal Nursing for Longer Dynamic Video Synthesis.
CoRR, 2024

Are Vision Language Models Texture or Shape Biased and Can We Steer Them?
CoRR, 2024

Implicit Representations for Constrained Image Segmentation.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

CosPGD: an efficient white-box adversarial attack for pixel-wise prediction tasks.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

MultiMax: Sparse and Multi-Modal Attention Learning.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

Adversarial Supervision Makes Layout-to-Image Diffusion Models Thrive.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

Task Driven Sensor Layouts - Joint Optimization of Pixel Layout and Network Parameters.
Proceedings of the IEEE International Conference on Computational Photography, 2024

Improving Feature Stability During Upsampling - Spectral Artifacts and the Importance of Spatial Context.
Proceedings of the Computer Vision - ECCV 2024, 2024

2023
Improving Native CNN Robustness with Filter Frequency Regularization.
Trans. Mach. Learn. Res., 2023

Higher-Order Multicuts for Geometric Model Fitting and Motion Segmentation.
IEEE Trans. Pattern Anal. Mach. Intell., 2023

Improving Stability during Upsampling - on the Importance of Spatial Context.
CoRR, 2023

As large as it gets: Learning infinitely large Filters via Neural Implicit Functions in the Fourier Domain.
CoRR, 2023

Fix your downsampling ASAP! Be natively more robust via Aliasing and Spectral Artifact free Pooling.
CoRR, 2023

An Evaluation of Zero-Cost Proxies - from Neural Architecture Performance to Model Robustness.
CoRR, 2023

Happy People - Image Synthesis as Black-Box Optimization Problem in the Discrete Latent Space of Deep Generative Models.
CoRR, 2023

Overcoming Topology Agnosticism: Enhancing Skeleton-Based Action Recognition through Redefined Skeletal Topology Awareness.
CoRR, 2023

Differentiable Sensor Layouts for End-to-End Learning of Task-Specific Camera Parameters.
CoRR, 2023

CosPGD: a unified white-box adversarial attack for pixel-wise prediction tasks.
CoRR, 2023

Intra-Source Style Augmentation for Improved Domain Generalization.
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2023

Unfolding Local Growth Rate Estimates for (Almost) Perfect Adversarial Detection.
Proceedings of the 18th International Joint Conference on Computer Vision, 2023

Neural Architecture Design and Robustness: A Dataset.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

Classification robustness to common optical aberrations.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

On the unreasonable vulnerability of transformers for image restoration - and an easy fix.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

Local Spherical Harmonics Improve Skeleton-Based Hand Action Recognition.
Proceedings of the Pattern Recognition - 45th DAGM German Conference, 2023

FullFormer: Generating Shapes Inside Shapes.
Proceedings of the Pattern Recognition - 45th DAGM German Conference, 2023

An Evaluation of Zero-Cost Proxies - From Neural Architecture Performance Prediction to Model Robustness.
Proceedings of the Pattern Recognition - 45th DAGM German Conference, 2023

An Extended Study of Human-like Behavior under Adversarial Training.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

Divide & Bind Your Attention for Improved Generative Semantic Nursing.
Proceedings of the 34th British Machine Vision Conference 2023, 2023

2022
Aliasing and adversarial robust generalization of CNNs.
Mach. Learn., 2022

Hypergraph Transformer for Skeleton-based Action Recognition.
CoRR, 2022

FrequencyLowCut Pooling - Plug & Play against Catastrophic Overfitting.
CoRR, 2022

Learning to Solve Minimum Cost Multicuts Efficiently Using Edge-Weighted Graph Convolutional Neural Networks.
Proceedings of the Machine Learning and Knowledge Discovery in Databases, 2022

Trading off Image Quality for Robustness is not Necessary with Regularized Deterministic Autoencoders.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Robust Models are less Over-Confident.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Surrogate NAS Benchmarks: Going Beyond the Limited Search Spaces of Tabular NAS Benchmarks.
Proceedings of the Tenth International Conference on Learning Representations, 2022

Learning Where to Look - Generative NAS is Surprisingly Efficient.
Proceedings of the Computer Vision - ECCV 2022, 2022

FrequencyLowCut Pooling - Plug and Play Against Catastrophic Overfitting.
Proceedings of the Computer Vision - ECCV 2022, 2022

Optimizing Edge Detection for Image Segmentation with Multicut Penalties.
Proceedings of the Pattern Recognition, 2022

SP-ViT: Learning 2D Spatial Priors for Vision Transformers.
Proceedings of the 33rd British Machine Vision Conference 2022, 2022

2021
Arrow R-CNN for handwritten diagram recognition.
Int. J. Document Anal. Recognit., 2021

Is RobustBench/AutoAttack a suitable Benchmark for Adversarial Robustness?
CoRR, 2021

Detecting AutoAttack Perturbations in the Frequency Domain.
CoRR, 2021

DARTS for Inverse Problems: a Study on Hyperparameter Sensitivity.
CoRR, 2021

Estimating the Robustness of Classification Models by the Structure of the Learned Feature-Space.
CoRR, 2021

Uncertainty in minimum cost multicuts for image and motion segmentation.
Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence, 2021

MSM: Multi-stage Multicuts for Scalable Image Clustering.
Proceedings of the High Performance Computing - ISC High Performance Digital 2021 International Workshops, Frankfurt am Main, Germany, June 24, 2021

Shape your Space: A Gaussian Mixture Regularization Approach to Deterministic Autoencoders.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Smooth Variational Graph Embeddings for Efficient Neural Architecture Search.
Proceedings of the International Joint Conference on Neural Networks, 2021

SpectralDefense: Detecting Adversarial Attacks on CNNs in the Fourier Domain.
Proceedings of the International Joint Conference on Neural Networks, 2021

Beyond the Spectrum: Detecting Deepfakes via Re-Synthesis.
Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, 2021

Multi-Class Multi-Instance Count Conditioned Adversarial Image Generation.
Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021

Spectral Distribution Aware Image Generation.
Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021

2020
Motion Segmentation & Multiple Object Tracking by Correlation Co-Clustering.
IEEE Trans. Pattern Anal. Mach. Intell., 2020

Smooth Variational Graph Embeddings for Efficient Neural Architecture Search.
CoRR, 2020

NAS-Bench-301 and the Case for Surrogate Benchmarks for Neural Architecture Search.
CoRR, 2020

Unsupervised Multiple Person Tracking using AutoEncoder-Based Lifted Multicuts.
CoRR, 2020

A Benders Decomposition Approach to Correlation Clustering.
Proceedings of the 6th IEEE/ACM Workshop on Machine Learning in High Performance Computing Environments, 2020

Object Segmentation Tracking from Generic Video Cues.
Proceedings of the 25th International Conference on Pattern Recognition, 2020

Learning Embeddings for Image Clustering: An Empirical Study of Triplet Loss Approaches.
Proceedings of the 25th International Conference on Pattern Recognition, 2020

Unsupervised Bootstrapping of Active Learning for Entity Resolution.
Proceedings of the Semantic Web - 17th International Conference, 2020

Neural Architecture Performance Prediction Using Graph Neural Networks.
Proceedings of the Pattern Recognition - 42nd DAGM German Conference, DAGM GCPR 2020, Tübingen, Germany, September 28, 2020

Watch Your Up-Convolution: CNN Based Generative Deep Neural Networks Are Failing to Reproduce Spectral Distributions.
Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020

Self-supervised Sparse to Dense Motion Segmentation.
Proceedings of the Computer Vision - ACCV 2020 - 15th Asian Conference on Computer Vision, Kyoto, Japan, November 30, 2020

A Two-Stage Minimum Cost Multicut Approach to Self-supervised Multiple Person Tracking.
Proceedings of the Computer Vision - ACCV 2020 - 15th Asian Conference on Computer Vision, Kyoto, Japan, November 30, 2020

2019
A Variational-Sequential Graph Autoencoder for Neural Architecture Performance Prediction.
CoRR, 2019

Unmasking DeepFakes with simple Features.
CoRR, 2019

Massively Parallel Benders Decomposition for Correlation Clustering.
CoRR, 2019

2018
Occlusions, Motion and Depth Boundaries with a Generic Network for Disparity, Optical Flow or Scene Flow Estimation.
Proceedings of the Computer Vision - ECCV 2018, 2018

Solving Minimum Cost Lifted Multicut Problems by Node Agglomeration.
Proceedings of the Computer Vision - ACCV 2018, 2018

2017
ProbFlow: Joint Optical Flow and Uncertainty Estimation.
Proceedings of the IEEE International Conference on Computer Vision, 2017

Higher-Order Minimum Cost Lifted Multicuts for Motion Segmentation.
Proceedings of the IEEE International Conference on Computer Vision, 2017

Learning Dilation Factors for Semantic Segmentation of Street Scenes.
Proceedings of the Pattern Recognition - 39th German Conference, 2017

FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks.
Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, 2017

STD2P: RGBD Semantic Segmentation Using Spatio-Temporal Data-Driven Pooling.
Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, 2017

2016
A Multi-cut Formulation for Joint Segmentation and Tracking of Multiple Objects.
CoRR, 2016

RGBD Semantic Segmentation Using Spatio-Temporal Data-Driven Pooling.
CoRR, 2016

Point-Wise Mutual Information-Based Video Segmentation with High Temporal Consistency.
Proceedings of the Computer Vision - ECCV 2016 Workshops, 2016

Segmentation in Point Clouds from RGB-D Using Spectral Graph Reduction.
Proceedings of the Perspectives in Shape Analysis, 2016

2015
Efficient Decomposition of Image and Mesh Graphs by Lifted Multicuts.
Proceedings of the 2015 IEEE International Conference on Computer Vision, 2015

Motion Trajectory Segmentation via Minimum Cost Multicuts.
Proceedings of the 2015 IEEE International Conference on Computer Vision, 2015

2014
Spectral Graph Reduction for Efficient Image and Streaming Video Segmentation.
Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition, 2014

2013
Variational attenuation correction in two-view confocal microscopy.
BMC Bioinform., 2013

Variational attenuation correction of two-view confocal microscopic recordings.
Proceedings of the 10th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, 2013

Blind Deconvolution of Widefield Fluorescence Microscopic Data by Regularization of the Optical Transfer Function (OTF).
Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition, 2013

2012
Blind deconvolution with PSF regularization for wide-field microscopy.
Proceedings of the 9th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, 2012

Modeling of Sparsely Sampled Tubular Surfaces Using Coupled Curves.
Proceedings of the Pattern Recognition, 2012

2011
Hierarchical Markov Random Fields for mast cell segmentation in electron microscopic recordings.
Proceedings of the 8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, 2011

2010
Evaluation of a New Point Clouds Registration Method Based on Group Averaging Features.
Proceedings of the 20th International Conference on Pattern Recognition, 2010

3D Deformable Surfaces with Locally Self-Adjusting Parameters - A Robust Method to Determine Cell Nucleus Shapes.
Proceedings of the 20th International Conference on Pattern Recognition, 2010

Mean Shift Gradient Vector Flow: A Robust External Force Field for 3D Active Surfaces.
Proceedings of the 20th International Conference on Pattern Recognition, 2010

Semi-supervised Learning of Edge Filters for Volumetric Image Segmentation.
Proceedings of the Pattern Recognition, 2010

2009
A 3D Active Surface Model for the Accurate Segmentation of <i>Drosophila</i> Schneider Cell Nuclei and Nucleoli.
Proceedings of the Advances in Visual Computing, 5th International Symposium, 2009


  Loading...