Matthias Hein

Affiliations:
  • Max Planck Institute for Intelligent Systems, Tübingen, Germany
  • Faculty of Mathematics and Computer Science, Saarland University
  • Max Planck Institute for Biological Cybernetics, Tübingen, Germany


According to our database1, Matthias Hein authored at least 150 papers between 2003 and 2024.

Collaborative distances:

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2024
LoGex: Improved tail detection of extremely rare histopathology classes via guided diffusion.
CoRR, 2024

How to train your ViT for OOD Detection.
CoRR, 2024

Zero-Shot Distillation for Image Encoders: How to Make Effective Use of Synthetic Data.
CoRR, 2024

Identification of Fine-grained Systematic Errors via Controlled Scene Generation.
CoRR, 2024

Segment (Almost) Nothing: Prompt-Agnostic Adversarial Attacks on Segmentation Models.
Proceedings of the IEEE Conference on Secure and Trustworthy Machine Learning, 2024

Segmentation-Guided MRI Reconstruction for Meaningfully Diverse Reconstructions.
Proceedings of the Deep Generative Models - 4th MICCAI Workshop, 2024

Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

Bias of Stochastic Gradient Descent or the Architecture: Disentangling the Effects of Overparameterization of Neural Networks.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

DiG-IN: Diffusion Guidance for Investigating Networks - Uncovering Classifier Differences, Neuron Visualisations, and Visual Counterfactual Explanations.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

2023
Nonlinear Perron-Frobenius Theorems for Nonnegative Tensors.
SIAM Rev., May, 2023

Random and Adversarial Bit Error Robustness: Energy-Efficient and Secure DNN Accelerators.
IEEE Trans. Pattern Anal. Mach. Intell., March, 2023

Analyzing and Explaining Image Classifiers via Diffusion Guidance.
CoRR, 2023

Generating Realistic Counterfactuals for Retinal Fundus and OCT Images using Diffusion Models.
CoRR, 2023

Robust Semantic Segmentation: Strong Adversarial Attacks and Fast Training of Robust Models.
CoRR, 2023

Revisiting Adversarial Training for ImageNet: Architectures, Training and Generalization across Threat Models.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Normalization Layers Are All That Sharpness-Aware Minimization Needs.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Improving l1-Certified Robustness via Randomized Smoothing by Leveraging Box Constraints.
Proceedings of the International Conference on Machine Learning, 2023

In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluation.
Proceedings of the International Conference on Machine Learning, 2023

A Modern Look at the Relationship between Sharpness and Generalization.
Proceedings of the International Conference on Machine Learning, 2023

Certified Defences Against Adversarial Patch Attacks on Semantic Segmentation.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

Sound Randomized Smoothing in Floating-Point Arithmetic.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

On the Adversarial Robustness of Multi-Modal Foundation Models.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

Identifying Systematic Errors in Object Detectors with the SCROD Pipeline.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

Spurious Features Everywhere - Large-Scale Detection of Harmful Spurious Features in ImageNet.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

2022
On the interplay of adversarial robustness and architecture components: patches, convolution and attention.
CoRR, 2022

Sound Randomized Smoothing in Floating-Point Arithmetics.
CoRR, 2022

Neural Network Heuristic Functions: Taking Confidence into Account.
Proceedings of the Fifteenth International Symposium on Combinatorial Search, 2022

Provably Adversarially Robust Detection of Out-of-Distribution Data (Almost) for Free.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Diffusion Visual Counterfactual Explanations.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Adversarial Robustness of MR Image Reconstruction Under Realistic Perturbations.
Proceedings of the Machine Learning for Medical Image Reconstruction, 2022

Visual Explanations for the Detection of Diabetic Retinopathy from Retinal Fundus Images.
Proceedings of the Medical Image Computing and Computer Assisted Intervention - MICCAI 2022, 2022

Provably Adversarially Robust Nearest Prototype Classifiers.
Proceedings of the International Conference on Machine Learning, 2022

Evaluating the Adversarial Robustness of Adaptive Test-time Defenses.
Proceedings of the International Conference on Machine Learning, 2022

Adversarial Robustness against Multiple and Single l<sub>p</sub>-Threat Models via Quick Fine-Tuning of Robust Classifiers.
Proceedings of the International Conference on Machine Learning, 2022

Breaking Down Out-of-Distribution Detection: Many Methods Based on OOD Training Data Estimate a Combination of the Same Core Quantities.
Proceedings of the International Conference on Machine Learning, 2022

Sparse Visual Counterfactual Explanations in Image Space.
Proceedings of the Pattern Recognition, 2022

Being a Bit Frequentist Improves Bayesian Neural Networks.
Proceedings of the International Conference on Artificial Intelligence and Statistics, 2022

Sparse-RS: A Versatile Framework for Query-Efficient Sparse Black-Box Adversarial Attacks.
Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence, 2022

2021
The Global Convergence of the Nonlinear Power Method for Mixed-Subordinate Matrix Norms.
J. Sci. Comput., 2021

Provably Robust Detection of Out-of-distribution Data (almost) for free.
CoRR, 2021

Adversarial robustness against multiple l<sub>p</sub>-threat models at the price of one and how to quickly fine-tune robust models to another threat model.
CoRR, 2021

Learnable uncertainty under Laplace approximations.
Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence, 2021

Meta-Learning the Search Distribution of Black-Box Random Search Based Adversarial Attacks.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

An Infinite-Feature Extension for Bayesian ReLU Nets That Fixes Their Asymptotic Overconfidence.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

RobustBench: a standardized adversarial robustness benchmark.
Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks 1, 2021

Bit Error Robustness for Energy-Efficient DNN Accelerators.
Proceedings of the Fourth Conference on Machine Learning and Systems, 2021

Mind the Box: l<sub>1</sub>-APGD for Sparse Adversarial Attacks on Image Classifiers.
Proceedings of the 38th International Conference on Machine Learning, 2021

Relating Adversarially Robust Generalization to Flat Minima.
Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021

2020
Scaling up the Randomized Gradient-Free Adversarial Attack Reveals Overestimation of Robustness Using Established Attacks.
Int. J. Comput. Vis., 2020

Error Estimates for Spectral Convergence of the Graph Laplacian on Random Geometric Graphs Toward the Laplace-Beltrami Operator.
Found. Comput. Math., 2020

Out-distribution aware Self-training in an Open World Setting.
CoRR, 2020

RobustBench: a standardized adversarial robustness benchmark.
CoRR, 2020

Fixing Asymptotic Uncertainty of Bayesian Neural Networks with Infinite ReLU Features.
CoRR, 2020

Provable Worst Case Guarantees for the Detection of Out-of-Distribution Data.
CoRR, 2020

On Mitigating Random and Adversarial Bit Errors.
CoRR, 2020

Computing the norm of nonnegative matrices and the log-Sobolev constant of Markov chains.
CoRR, 2020

Certifiably Adversarially Robust Detection of Out-of-Distribution Data.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Confidence-Calibrated Adversarial Training: Generalizing to Unseen Attacks.
Proceedings of the 37th International Conference on Machine Learning, 2020

Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networks.
Proceedings of the 37th International Conference on Machine Learning, 2020

Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks.
Proceedings of the 37th International Conference on Machine Learning, 2020

Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attack.
Proceedings of the 37th International Conference on Machine Learning, 2020

Towards neural networks that provably know when they don't know.
Proceedings of the 8th International Conference on Learning Representations, 2020

Provable robustness against all adversarial $l_p$-perturbations for $p\geq 1$.
Proceedings of the 8th International Conference on Learning Representations, 2020

Adversarial Robustness on In- and Out-Distribution Improves Explainability.
Proceedings of the Computer Vision - ECCV 2020, 2020

Square Attack: A Query-Efficient Black-Box Adversarial Attack via Random Search.
Proceedings of the Computer Vision - ECCV 2020, 2020

2019
A Unifying Perron-Frobenius Theorem for Nonnegative Tensors via Multihomogeneous Maps.
SIAM J. Matrix Anal. Appl., 2019

The Perron-Frobenius Theorem for Multihomogeneous Mappings.
SIAM J. Matrix Anal. Appl., 2019

Confidence-Calibrated Adversarial Training: Towards Robust Models Generalizing Beyond the Attack Used During Training.
CoRR, 2019

Provable robustness against all adversarial l<sub>p</sub>-perturbations for p≥1.
CoRR, 2019

Provably robust boosted decision stumps and trees against adversarial attacks.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Generalized Matrix Means for Semi-Supervised Learning with Multilayer Graphs.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Spectral Clustering of Signed Graphs via Matrix Power Means.
Proceedings of the 36th International Conference on Machine Learning, 2019

On the loss landscape of a class of deep neural networks with no bad local valleys.
Proceedings of the 7th International Conference on Learning Representations, 2019

Sparse and Imperceivable Adversarial Attacks.
Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision, 2019

Disentangling Adversarial Robustness and Generalization.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019

Why ReLU Networks Yield High-Confidence Predictions Far Away From the Training Data and How to Mitigate the Problem.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019

Provable Robustness of ReLU networks via Maximization of Linear Regions.
Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics, 2019

2018
Community Detection in Networks via Nonlinear Modularity Eigenvectors.
SIAM J. Appl. Math., 2018

Analysis and Optimization of Loss Functions for Multiclass, Top-k, and Multilabel Classification.
IEEE Trans. Pattern Anal. Mach. Intell., 2018

Logit Pairing Methods Can Fool Gradient-Based Attacks.
CoRR, 2018

A unifying Perron-Frobenius theorem for nonnegative tensors via multi-homogeneous maps.
CoRR, 2018

Neural Networks Should Be Wide Enough to Learn Disconnected Decision Regions.
Proceedings of the 35th International Conference on Machine Learning, 2018

Optimization Landscape and Expressivity of Deep CNNs.
Proceedings of the 35th International Conference on Machine Learning, 2018

The loss surface and expressivity of deep convolutional neural networks.
Proceedings of the 6th International Conference on Learning Representations, 2018

A Randomized Gradient-Free Attack on ReLU Networks.
Proceedings of the Pattern Recognition - 40th German Conference, 2018

The Power Mean Laplacian for Multilayer Graph Clustering.
Proceedings of the International Conference on Artificial Intelligence and Statistics, 2018

2017
An Efficient Multilinear Optimization Framework for Hypergraph Matching.
IEEE Trans. Pattern Anal. Mach. Intell., 2017

Formal Guarantees on the Robustness of a Classifier against Adversarial Manipulation.
Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

The Loss Surface of Deep and Wide Neural Networks.
Proceedings of the 34th International Conference on Machine Learning, 2017

Variants of RMSProp and Adagrad with Logarithmic Regret Bounds.
Proceedings of the 34th International Conference on Machine Learning, 2017

Simple Does It: Weakly Supervised Instance and Semantic Segmentation.
Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, 2017

2016
Nodal domain theorem for the graph p-Laplacian.
CoRR, 2016

Weakly Supervised Semantic Labelling and Instance Segmentation.
CoRR, 2016

Clustering Signed Networks with the Geometric Mean of Laplacians.
Proceedings of the Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, 2016

Globally Optimal Training of Generalized Polynomial Neural Networks with Nonlinear Spectral Methods.
Proceedings of the Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, 2016

Improved Image Boundaries for Better Video Segmentation.
Proceedings of the Computer Vision - ECCV 2016 Workshops, 2016

Latent Embeddings for Zero-Shot Classification.
Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, 2016

Loss Functions for Top-k Error: Analysis and Insights.
Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, 2016

Weakly Supervised Object Boundaries.
Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, 2016

2015
Correction of noisy labels via mutual consistency check.
Neurocomputing, 2015

Mathematical and Computational Foundations of Learning Theory (Dagstuhl Seminar 15361).
Dagstuhl Reports, 2015

Regularization-Free Estimation in Trace Regression with Symmetric Positive Semidefinite Matrices.
Proceedings of the Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015, 2015

Top-k Multiclass SVM.
Proceedings of the Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015, 2015

Efficient Output Kernel Learning for Multiple Tasks.
Proceedings of the Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015, 2015

A flexible tensor block coordinate ascent scheme for hypergraph matching.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015

Classifier based graph construction for video segmentation.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015

2014
Learning using privileged information: SV M+ and weighted SVM.
Neural Networks, 2014

Hitting and commute times in large random neighborhood graphs.
J. Mach. Learn. Res., 2014

Tight Continuous Relaxation of the Balanced k-Cut Problem.
Proceedings of the Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014, 2014

Robust PCA: Optimization of the Robust Reconstruction Error Over the Stiefel Manifold.
Proceedings of the Pattern Recognition - 36th German Conference, 2014

Learning Must-Link Constraints for Video Segmentation Based on Spectral Clustering.
Proceedings of the Pattern Recognition - 36th German Conference, 2014

Scalable Multitask Representation Learning for Scene Classification.
Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition, 2014

2013
Learning Using Privileged Information: SVM+ and Weighted SVM.
CoRR, 2013

Nonlinear Eigenproblems in Data Analysis - Balanced Graph Cuts and the RatioDCA-Prox.
CoRR, 2013

Towards realistic team formation in social networks based on densest subgraphs.
Proceedings of the 22nd International World Wide Web Conference, 2013

Matrix factorization with binary components.
Proceedings of the Advances in Neural Information Processing Systems 26: 27th Annual Conference on Neural Information Processing Systems 2013. Proceedings of a meeting held December 5-8, 2013

The Total Variation on Hypergraphs - Learning on Hypergraphs Revisited.
Proceedings of the Advances in Neural Information Processing Systems 26: 27th Annual Conference on Neural Information Processing Systems 2013. Proceedings of a meeting held December 5-8, 2013

Constrained fractional set programs and their application in local clustering and community detection.
Proceedings of the 30th International Conference on Machine Learning, 2013

2012
Constrained 1-Spectral Clustering.
Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics, 2012

Isotope pattern deconvolution for peptide mass spectrometry by non-negative least squares/least absolute deviation template matching.
BMC Bioinform., 2012

2011
Mathematical and Computational Foundations of Learning Theory (Dagstuhl Seminar 11291).
Dagstuhl Reports, 2011

How the result of graph clustering methods depends on the construction of the graph
CoRR, 2011

Sparse recovery by thresholded non-negative least squares.
Proceedings of the Advances in Neural Information Processing Systems 24: 25th Annual Conference on Neural Information Processing Systems 2011. Proceedings of a meeting held 12-14 December 2011, 2011

Beyond Spectral Clustering - Tight Relaxations of Balanced Graph Cuts.
Proceedings of the Advances in Neural Information Processing Systems 24: 25th Annual Conference on Neural Information Processing Systems 2011. Proceedings of a meeting held 12-14 December 2011, 2011

2010
Nonparametric Regression between General Riemannian Manifolds.
SIAM J. Imaging Sci., 2010

Hitting times, commute distances and the spectral gap for large random geometric graphs
CoRR, 2010

Getting lost in space: Large sample analysis of the resistance distance.
Proceedings of the Advances in Neural Information Processing Systems 23: 24th Annual Conference on Neural Information Processing Systems 2010. Proceedings of a meeting held 6-9 December 2010, 2010

An Inverse Power Method for Nonlinear Eigenproblems with Applications in 1-Spectral Clustering and Sparse PCA.
Proceedings of the Advances in Neural Information Processing Systems 23: 24th Annual Conference on Neural Information Processing Systems 2010. Proceedings of a meeting held 6-9 December 2010, 2010

2009
Optimal construction of k-nearest-neighbor graphs for identifying noisy clusters.
Theor. Comput. Sci., 2009

Large-scale antibody profiling of human blood sera: The future of molecular diagnosis.
Inform. Spektrum, 2009

Semi-supervised Regression using Hessian energy with an application to semi-supervised dimensionality reduction.
Proceedings of the Advances in Neural Information Processing Systems 22: 23rd Annual Conference on Neural Information Processing Systems 2009. Proceedings of a meeting held 7-10 December 2009, 2009

Robust Nonparametric Regression with Metric-Space Valued Output.
Proceedings of the Advances in Neural Information Processing Systems 22: 23rd Annual Conference on Neural Information Processing Systems 2009. Proceedings of a meeting held 7-10 December 2009, 2009

Spectral clustering based on the graph <i>p</i>-Laplacian.
Proceedings of the 26th Annual International Conference on Machine Learning, 2009

2008
Manifold-valued Thin-Plate Splines with Applications in Computer Graphics.
Comput. Graph. Forum, 2008

Enhancement of Bright Video Features for HDR Displays.
Comput. Graph. Forum, 2008

Non-parametric Regression Between Manifolds.
Proceedings of the Advances in Neural Information Processing Systems 21, 2008

Influence of graph construction on graph-based clustering measures.
Proceedings of the Advances in Neural Information Processing Systems 21, 2008

2007
Graph Laplacians and their Convergence on Random Neighborhood Graphs.
J. Mach. Learn. Res., 2007

Cluster Identification in Nearest-Neighbor Graphs.
Proceedings of the Algorithmic Learning Theory, 18th International Conference, 2007

Manifold Denoising as Preprocessing for Finding Natural Representations of Data.
Proceedings of the Twenty-Second AAAI Conference on Artificial Intelligence, 2007

2006
Manifold Denoising.
Proceedings of the Advances in Neural Information Processing Systems 19, 2006

Uniform Convergence of Adaptive Graph-Based Regularization.
Proceedings of the Learning Theory, 19th Annual Conference on Learning Theory, 2006

2005
Geometrical aspects of statistical learning theory.
PhD thesis, 2005

Maximal margin classification for metric spaces.
J. Comput. Syst. Sci., 2005

Intrinsic dimensionality estimation of submanifolds in R<sup>d</sup>.
Proceedings of the Machine Learning, 2005

From Graphs to Manifolds - Weak and Strong Pointwise Consistency of Graph Laplacians.
Proceedings of the Learning Theory, 18th Annual Conference on Learning Theory, 2005

Hilbertian Metrics and Positive Definite Kernels on Probability Measures.
Proceedings of the Tenth International Workshop on Artificial Intelligence and Statistics, 2005

2004
Hilbertian Metrics on Probability Measures and Their Application in SVM?s.
Proceedings of the Pattern Recognition, 26th DAGM Symposium, August 30, 2004

2003
Measure Based Regularization.
Proceedings of the Advances in Neural Information Processing Systems 16 [Neural Information Processing Systems, 2003

Maximal Margin Classification for Metric Spaces.
Proceedings of the Computational Learning Theory and Kernel Machines, 2003


  Loading...