default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDMatthias Hein 0001
Person information
- affiliation: Max Planck Institute for Intelligent Systems, Tübingen, Germany
- affiliation: Faculty of Mathematics and Computer Science, Saarland University
- affiliation: Max Planck Institute for Biological Cybernetics, Tübingen, Germany
Other persons with the same name
- Matthias Hein 0002
![[0000-0002-8751-7760]](https://dblp.uni-trier.de./img/orcid-mark.12x12.png "0000-0002-8751-7760")
(aka: Matthias A. Hein) — Technische Universität Ilmenau, Faculty of Computer Science and Automation, Germany - Matthias Hein 0003 — University of Wuppertal, Department of Physics, Germany
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
showing all ?? records
2020 – today
- 2024
[c101]Maximilian Augustin, Yannic Neuhaus, Matthias Hein:
DiG-IN: Diffusion Guidance for Investigating Networks - Uncovering Classifier Differences, Neuron Visualisations, and Visual Counterfactual Explanations. CVPR 2024: 11093-11103- [c100]Francesco Croce, Naman D. Singh, Matthias Hein:
Towards Reliable Evaluation and Fast Training of Robust Semantic Segmentation Models. ECCV (79) 2024: 180-197 - [c99]Amit Peleg, Matthias Hein:
Bias of Stochastic Gradient Descent or the Architecture: Disentangling the Effects of Overparameterization of Neural Networks. ICML 2024 - [c98]Christian Schlarmann, Naman Deep Singh, Francesco Croce, Matthias Hein:
Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models. ICML 2024 - [c97]Jan Nikolas Morshuis, Matthias Hein, Christian F. Baumgartner:
Segmentation-Guided MRI Reconstruction for Meaningfully Diverse Reconstructions. DGM4MICCAI@MICCAI 2024: 180-190 - [c96]Francesco Croce, Matthias Hein:
Segment (Almost) Nothing: Prompt-Agnostic Adversarial Attacks on Segmentation Models. SaTML 2024: 425-442 - [i101]Christian Schlarmann, Naman Deep Singh, Francesco Croce, Matthias Hein:
Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models. CoRR abs/2402.12336 (2024) - [i100]Valentyn Boreiko, Matthias Hein, Jan Hendrik Metzen:
Identification of Fine-grained Systematic Errors via Controlled Scene Generation. CoRR abs/2404.07045 (2024) - [i99]Niclas Popp, Jan Hendrik Metzen, Matthias Hein:
Zero-Shot Distillation for Image Encoders: How to Make Effective Use of Synthetic Data. CoRR abs/2404.16637 (2024) - [i98]Maximilian Müller, Matthias Hein:
How to train your ViT for OOD Detection. CoRR abs/2405.17447 (2024) - [i97]Amit Peleg, Matthias Hein:
Bias of Stochastic Gradient Descent or the Architecture: Disentangling the Effects of Overparameterization of Neural Networks. CoRR abs/2407.03848 (2024) - [i96]Jan Nikolas Morshuis, Matthias Hein, Christian F. Baumgartner:
Segmentation-guided MRI reconstruction for meaningfully diverse reconstructions. CoRR abs/2407.18026 (2024) - [i95]Maximilian Müller, Matthias Hein:
LoGex: Improved tail detection of extremely rare histopathology classes via guided diffusion. CoRR abs/2409.01317 (2024) - [i94]Valentyn Boreiko, Alexander Panfilov, Václav Vorácek, Matthias Hein, Jonas Geiping:
A Realistic Threat Model for Large Language Model Jailbreaks. CoRR abs/2410.16222 (2024) - [i93]Naman Deep Singh, Francesco Croce, Matthias Hein:
Perturb and Recover: Fine-tuning for Effective Backdoor Removal from CLIP. CoRR abs/2412.00727 (2024) - [i92]Niclas Popp, Dan Zhang, Jan Hendrik Metzen, Matthias Hein, Lukas Schott:
Object-Focused Data Selection for Dense Prediction Tasks. CoRR abs/2412.10032 (2024) - 2023
- [j21]David Stutz, Nandhini Chandramoorthy, Matthias Hein, Bernt Schiele:
Random and Adversarial Bit Error Robustness: Energy-Efficient and Secure DNN Accelerators. IEEE Trans. Pattern Anal. Mach. Intell. 45(3): 3632-3647 (2023) - [j20]Antoine Gautier, Francesco Tudisco, Matthias Hein:
Nonlinear Perron-Frobenius Theorems for Nonnegative Tensors. SIAM Rev. 65(2): 495-536 (2023) - [c95]Yannic Neuhaus, Maximilian Augustin, Valentyn Boreiko, Matthias Hein:
Spurious Features Everywhere - Large-Scale Detection of Harmful Spurious Features in ImageNet. ICCV 2023: 20178-20189 - [c94]Christian Schlarmann, Matthias Hein:
On the Adversarial Robustness of Multi-Modal Foundation Models. ICCV (Workshops) 2023: 3679-3687 - [c93]Valentyn Boreiko, Matthias Hein, Jan Hendrik Metzen:
Identifying Systematic Errors in Object Detectors with the SCROD Pipeline. ICCV (Workshops) 2023: 4092-4101 - [c92]Václav Vorácek, Matthias Hein:
Sound Randomized Smoothing in Floating-Point Arithmetic. ICLR 2023 - [c91]Maksym Yatsura, Kaspar Sakmann, N. Grace Hua, Matthias Hein, Jan Hendrik Metzen:
Certified Defences Against Adversarial Patch Attacks on Semantic Segmentation. ICLR 2023 - [c90]Maksym Andriushchenko, Francesco Croce, Maximilian Müller, Matthias Hein, Nicolas Flammarion:
A Modern Look at the Relationship between Sharpness and Generalization. ICML 2023: 840-902 - [c89]Julian Bitterwolf, Maximilian Müller, Matthias Hein:
In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluation. ICML 2023: 2471-2506 - [c88]Václav Vorácek, Matthias Hein:
Improving l1-Certified Robustness via Randomized Smoothing by Leveraging Box Constraints. ICML 2023: 35198-35222 - [c87]Maximilian Müller, Tiffany Vlaar, David Rolnick, Matthias Hein:
Normalization Layers Are All That Sharpness-Aware Minimization Needs. NeurIPS 2023 - [c86]Naman Deep Singh, Francesco Croce, Matthias Hein:
Revisiting Adversarial Training for ImageNet: Architectures, Training and Generalization across Threat Models. NeurIPS 2023 - [i91]Maksym Andriushchenko, Francesco Croce, Maximilian Müller, Matthias Hein, Nicolas Flammarion:
A modern look at the relationship between sharpness and generalization. CoRR abs/2302.07011 (2023) - [i90]Naman D. Singh, Francesco Croce, Matthias Hein:
Revisiting Adversarial Training for ImageNet: Architectures, Training and Generalization across Threat Models. CoRR abs/2303.01870 (2023) - [i89]Julian Bitterwolf, Maximilian Müller, Matthias Hein:
In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluation. CoRR abs/2306.00826 (2023) - [i88]Maximilian Müller, Tiffany Vlaar, David Rolnick, Matthias Hein:
Normalization Layers Are All That Sharpness-Aware Minimization Needs. CoRR abs/2306.04226 (2023) - [i87]Francesco Croce, Naman D. Singh, Matthias Hein:
Robust Semantic Segmentation: Strong Adversarial Attacks and Fast Training of Robust Models. CoRR abs/2306.12941 (2023) - [i86]Christian Schlarmann, Matthias Hein:
On the Adversarial Robustness of Multi-Modal Foundation Models. CoRR abs/2308.10741 (2023) - [i85]Valentyn Boreiko, Matthias Hein, Jan Hendrik Metzen:
Identifying Systematic Errors in Object Detectors with the SCROD Pipeline. CoRR abs/2309.13489 (2023) - [i84]Indu Ilanchezian, Valentyn Boreiko, Laura Kühlewein, Ziwei Huang, Murat Seçkin Ayhan, Matthias Hein, Lisa M. Koch, Philipp Berens:
Generating Realistic Counterfactuals for Retinal Fundus and OCT Images using Diffusion Models. CoRR abs/2311.11629 (2023) - [i83]Francesco Croce, Matthias Hein:
Segment (Almost) Nothing: Prompt-Agnostic Adversarial Attacks on Segmentation Models. CoRR abs/2311.14450 (2023) - [i82]Maximilian Augustin, Yannic Neuhaus, Matthias Hein:
Analyzing and Explaining Image Classifiers via Diffusion Guidance. CoRR abs/2311.17833 (2023) - 2022
- [c85]Francesco Croce, Maksym Andriushchenko, Naman D. Singh, Nicolas Flammarion, Matthias Hein:
Sparse-RS: A Versatile Framework for Query-Efficient Sparse Black-Box Adversarial Attacks. AAAI 2022: 6437-6445 - [c84]Agustinus Kristiadi, Matthias Hein, Philipp Hennig:
Being a Bit Frequentist Improves Bayesian Neural Networks. AISTATS 2022: 529-545 - [c83]Valentyn Boreiko, Maximilian Augustin, Francesco Croce, Philipp Berens, Matthias Hein:
Sparse Visual Counterfactual Explanations in Image Space. GCPR 2022: 133-148 - [c82]Julian Bitterwolf, Alexander Meinke, Maximilian Augustin, Matthias Hein:
Breaking Down Out-of-Distribution Detection: Many Methods Based on OOD Training Data Estimate a Combination of the Same Core Quantities. ICML 2022: 2041-2074 - [c81]Francesco Croce, Sven Gowal, Thomas Brunner, Evan Shelhamer, Matthias Hein, A. Taylan Cemgil:
Evaluating the Adversarial Robustness of Adaptive Test-time Defenses. ICML 2022: 4421-4435 - [c80]Francesco Croce, Matthias Hein:
Adversarial Robustness against Multiple and Single lp-Threat Models via Quick Fine-Tuning of Robust Classifiers. ICML 2022: 4436-4454 - [c79]Václav Vorácek, Matthias Hein:
Provably Adversarially Robust Nearest Prototype Classifiers. ICML 2022: 22361-22383 - [c78]Jan Nikolas Morshuis, Sergios Gatidis, Matthias Hein, Christian F. Baumgartner:
Adversarial Robustness of MR Image Reconstruction Under Realistic Perturbations. MLMIR@MICCAI 2022: 24-33 - [c77]Valentyn Boreiko, Indu Ilanchezian, Murat Seçkin Ayhan, Sarah Müller, Lisa M. Koch, Hanna Faber, Philipp Berens, Matthias Hein:
Visual Explanations for the Detection of Diabetic Retinopathy from Retinal Fundus Images. MICCAI (2) 2022: 539-549 - [c76]Maximilian Augustin, Valentyn Boreiko, Francesco Croce, Matthias Hein:
Diffusion Visual Counterfactual Explanations. NeurIPS 2022 - [c75]Alexander Meinke, Julian Bitterwolf, Matthias Hein:
Provably Adversarially Robust Detection of Out-of-Distribution Data (Almost) for Free. NeurIPS 2022 - [c74]Daniel Heller, Patrick Ferber, Julian Bitterwolf, Matthias Hein, Jörg Hoffmann:
Neural Network Heuristic Functions: Taking Confidence into Account. SOCS 2022: 223-228 - [i81]Francesco Croce, Sven Gowal, Thomas Brunner, Evan Shelhamer, Matthias Hein, A. Taylan Cemgil:
Evaluating the Adversarial Robustness of Adaptive Test-time Defenses. CoRR abs/2202.13711 (2022) - [i80]Valentyn Boreiko, Maximilian Augustin, Francesco Croce, Philipp Berens, Matthias Hein:
Sparse Visual Counterfactual Explanations in Image Space. CoRR abs/2205.07972 (2022) - [i79]Julian Bitterwolf, Alexander Meinke, Maximilian Augustin, Matthias Hein:
Breaking Down Out-of-Distribution Detection: Many Methods Based on OOD Training Data Estimate a Combination of the Same Core Quantities. CoRR abs/2206.09880 (2022) - [i78]Václav Vorácek, Matthias Hein:
Provably Adversarially Robust Nearest Prototype Classifiers. CoRR abs/2207.07208 (2022) - [i77]Václav Vorácek, Matthias Hein:
Sound Randomized Smoothing in Floating-Point Arithmetics. CoRR abs/2207.07209 (2022) - [i76]Jan Nikolas Morshuis, Sergios Gatidis, Matthias Hein, Christian F. Baumgartner:
Adversarial Robustness of MR Image Reconstruction under Realistic Perturbations. CoRR abs/2208.03161 (2022) - [i75]Maksym Yatsura, Kaspar Sakmann, N. Grace Hua, Matthias Hein, Jan Hendrik Metzen:
Certified Defences Against Adversarial Patch Attacks on Semantic Segmentation. CoRR abs/2209.05980 (2022) - [i74]Francesco Croce, Matthias Hein:
On the interplay of adversarial robustness and architecture components: patches, convolution and attention. CoRR abs/2209.06953 (2022) - [i73]Maximilian Augustin, Valentyn Boreiko, Francesco Croce, Matthias Hein:
Diffusion Visual Counterfactual Explanations. CoRR abs/2210.11841 (2022) - [i72]Yannic Neuhaus, Maximilian Augustin, Valentyn Boreiko, Matthias Hein:
Spurious Features Everywhere - Large-Scale Detection of Harmful Spurious Features in ImageNet. CoRR abs/2212.04871 (2022) - 2021
- [j19]Antoine Gautier, Matthias Hein, Francesco Tudisco:
The Global Convergence of the Nonlinear Power Method for Mixed-Subordinate Matrix Norms. J. Sci. Comput. 88(1): 21 (2021) - [c73]David Stutz, Matthias Hein, Bernt Schiele:
Relating Adversarially Robust Generalization to Flat Minima. ICCV 2021: 7787-7797 - [c72]Francesco Croce, Matthias Hein:
Mind the Box: l1-APGD for Sparse Adversarial Attacks on Image Classifiers. ICML 2021: 2201-2211 - [c71]David Stutz, Nandhini Chandramoorthy, Matthias Hein, Bernt Schiele:
Bit Error Robustness for Energy-Efficient DNN Accelerators. MLSys 2021 - [c70]Francesco Croce, Maksym Andriushchenko, Vikash Sehwag, Edoardo Debenedetti, Nicolas Flammarion, Mung Chiang, Prateek Mittal, Matthias Hein:
RobustBench: a standardized adversarial robustness benchmark. NeurIPS Datasets and Benchmarks 2021 - [c69]Agustinus Kristiadi, Matthias Hein, Philipp Hennig:
An Infinite-Feature Extension for Bayesian ReLU Nets That Fixes Their Asymptotic Overconfidence. NeurIPS 2021: 18789-18800 - [c68]Maksym Yatsura, Jan Hendrik Metzen, Matthias Hein:
Meta-Learning the Search Distribution of Black-Box Random Search Based Adversarial Attacks. NeurIPS 2021: 30181-30195 - [c67]Agustinus Kristiadi, Matthias Hein, Philipp Hennig:
Learnable uncertainty under Laplace approximations. UAI 2021: 344-353 - [i71]Francesco Croce, Matthias Hein:
Mind the box: l1-APGD for sparse adversarial attacks on image classifiers. CoRR abs/2103.01208 (2021) - [i70]David Stutz, Matthias Hein, Bernt Schiele:
Relating Adversarially Robust Generalization to Flat Minima. CoRR abs/2104.04448 (2021) - [i69]David Stutz, Nandhini Chandramoorthy, Matthias Hein, Bernt Schiele:
Random and Adversarial Bit Error Robustness: Energy-Efficient and Secure DNN Accelerators. CoRR abs/2104.08323 (2021) - [i68]Francesco Croce, Matthias Hein:
Adversarial robustness against multiple lp-threat models at the price of one and how to quickly fine-tune robust models to another threat model. CoRR abs/2105.12508 (2021) - [i67]Alexander Meinke, Julian Bitterwolf, Matthias Hein:
Provably Robust Detection of Out-of-distribution Data (almost) for free. CoRR abs/2106.04260 (2021) - [i66]Agustinus Kristiadi, Matthias Hein, Philipp Hennig:
Being a Bit Frequentist Improves Bayesian Neural Networks. CoRR abs/2106.10065 (2021) - [i65]Maksym Yatsura, Jan Hendrik Metzen, Matthias Hein:
Meta-Learning the Search Distribution of Black-Box Random Search Based Adversarial Attacks. CoRR abs/2111.01714 (2021) - 2020
- [j18]Nicolás García Trillos, Moritz Gerlach, Matthias Hein, Dejan Slepcev:
Error Estimates for Spectral Convergence of the Graph Laplacian on Random Geometric Graphs Toward the Laplace-Beltrami Operator. Found. Comput. Math. 20(4): 827-887 (2020) - [j17]Francesco Croce, Jonas Rauber, Matthias Hein:
Scaling up the Randomized Gradient-Free Adversarial Attack Reveals Overestimation of Robustness Using Established Attacks. Int. J. Comput. Vis. 128(4): 1028-1046 (2020) - [c66]Maximilian Augustin, Alexander Meinke, Matthias Hein:
Adversarial Robustness on In- and Out-Distribution Improves Explainability. ECCV (26) 2020: 228-245 - [c65]Maksym Andriushchenko, Francesco Croce, Nicolas Flammarion, Matthias Hein:
Square Attack: A Query-Efficient Black-Box Adversarial Attack via Random Search. ECCV (23) 2020: 484-501 - [c64]Francesco Croce, Matthias Hein:
Provable robustness against all adversarial $l_p$-perturbations for $p\geq 1$. ICLR 2020 - [c63]Alexander Meinke, Matthias Hein:
Towards neural networks that provably know when they don't know. ICLR 2020 - [c62]Francesco Croce, Matthias Hein:
Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attack. ICML 2020: 2196-2205 - [c61]Francesco Croce, Matthias Hein:
Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks. ICML 2020: 2206-2216 - [c60]Agustinus Kristiadi, Matthias Hein, Philipp Hennig:
Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networks. ICML 2020: 5436-5446 - [c59]David Stutz, Matthias Hein, Bernt Schiele:
Confidence-Calibrated Adversarial Training: Generalizing to Unseen Attacks. ICML 2020: 9155-9166 - [c58]Julian Bitterwolf, Alexander Meinke, Matthias Hein:
Certifiably Adversarially Robust Detection of Out-of-Distribution Data. NeurIPS 2020 - [i64]Antoine Gautier, Matthias Hein, Francesco Tudisco:
Computing the norm of nonnegative matrices and the log-Sobolev constant of Markov chains. CoRR abs/2002.02447 (2020) - [i63]Agustinus Kristiadi, Matthias Hein, Philipp Hennig:
Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networks. CoRR abs/2002.10118 (2020) - [i62]Francesco Croce, Matthias Hein:
Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks. CoRR abs/2003.01690 (2020) - [i61]Maximilian Augustin, Alexander Meinke, Matthias Hein:
Adversarial Robustness on In- and Out-Distribution Improves Explainability. CoRR abs/2003.09461 (2020) - [i60]Francesco Croce, Maksym Andriushchenko, Naman D. Singh, Nicolas Flammarion, Matthias Hein:
Sparse-RS: a versatile framework for query-efficient sparse black-box adversarial attacks. CoRR abs/2006.12834 (2020) - [i59]David Stutz, Nandhini Chandramoorthy, Matthias Hein, Bernt Schiele:
On Mitigating Random and Adversarial Bit Errors. CoRR abs/2006.13977 (2020) - [i58]Julian Bitterwolf, Alexander Meinke, Matthias Hein:
Provable Worst Case Guarantees for the Detection of Out-of-Distribution Data. CoRR abs/2007.08473 (2020) - [i57]Agustinus Kristiadi, Matthias Hein, Philipp Hennig:
Fixing Asymptotic Uncertainty of Bayesian Neural Networks with Infinite ReLU Features. CoRR abs/2010.02709 (2020) - [i56]Agustinus Kristiadi, Matthias Hein, Philipp Hennig:
Learnable Uncertainty under Laplace Approximations. CoRR abs/2010.02720 (2020) - [i55]Francesco Croce, Maksym Andriushchenko, Vikash Sehwag, Nicolas Flammarion, Mung Chiang, Prateek Mittal, Matthias Hein:
RobustBench: a standardized adversarial robustness benchmark. CoRR abs/2010.09670 (2020) - [i54]Maximilian Augustin, Matthias Hein:
Out-distribution aware Self-training in an Open World Setting. CoRR abs/2012.12372 (2020)
2010 – 2019
- 2019
- [j16]Antoine Gautier, Francesco Tudisco, Matthias Hein:
The Perron-Frobenius Theorem for Multihomogeneous Mappings. SIAM J. Matrix Anal. Appl. 40(3): 1179-1205 (2019) - [j15]Antoine Gautier, Francesco Tudisco, Matthias Hein:
A Unifying Perron-Frobenius Theorem for Nonnegative Tensors via Multihomogeneous Maps. SIAM J. Matrix Anal. Appl. 40(3): 1206-1231 (2019) - [c57]Francesco Croce, Maksym Andriushchenko, Matthias Hein:
Provable Robustness of ReLU networks via Maximization of Linear Regions. AISTATS 2019: 2057-2066 - [c56]Matthias Hein, Maksym Andriushchenko, Julian Bitterwolf:
Why ReLU Networks Yield High-Confidence Predictions Far Away From the Training Data and How to Mitigate the Problem. CVPR 2019: 41-50 - [c55]Matthias Hein, Maksym Andriushchenko, Julian Bitterwolf:
Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problem. CVPR Workshops 2019: 58-74 - [c54]David Stutz, Matthias Hein, Bernt Schiele:
Disentangling Adversarial Robustness and Generalization. CVPR 2019: 6976-6987 - [c53]Francesco Croce, Matthias Hein:
Sparse and Imperceivable Adversarial Attacks. ICCV 2019: 4723-4731 - [c52]Quynh Nguyen, Mahesh Chandra Mukkamala, Matthias Hein:
On the loss landscape of a class of deep neural networks with no bad local valleys. ICLR (Poster) 2019 - [c51]Pedro Mercado, Francesco Tudisco, Matthias Hein:
Spectral Clustering of Signed Graphs via Matrix Power Means. ICML 2019: 4526-4536 - [c50]Maksym Andriushchenko, Matthias Hein:
Provably robust boosted decision stumps and trees against adversarial attacks. NeurIPS 2019: 12997-13008 - [c49]Pedro Mercado, Francesco Tudisco, Matthias Hein:
Generalized Matrix Means for Semi-Supervised Learning with Multilayer Graphs. NeurIPS 2019: 14848-14857 - [i53]Francesco Croce, Jonas Rauber, Matthias Hein:
Scaling up the randomized gradient-free adversarial attack reveals overestimation of robustness using established attacks. CoRR abs/1903.11359 (2019) - [i52]Pedro Mercado, Francesco Tudisco, Matthias Hein:
Spectral Clustering of Signed Graphs via Matrix Power Means. CoRR abs/1905.06230 (2019) - [i51]Francesco Croce, Matthias Hein:
Provable robustness against all adversarial lp-perturbations for p≥1. CoRR abs/1905.11213 (2019) - [i50]Maksym Andriushchenko, Matthias Hein:
Provably Robust Boosted Decision Stumps and Trees against Adversarial Attacks. CoRR abs/1906.03526 (2019) - [i49]Francesco Croce, Matthias Hein:
Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attack. CoRR abs/1907.02044 (2019) - [i48]Francesco Croce, Matthias Hein:
Sparse and Imperceivable Adversarial Attacks. CoRR abs/1909.05040 (2019) - [i47]Alexander Meinke, Matthias Hein:
Towards neural networks that provably know when they don't know. CoRR abs/1909.12180 (2019) - [i46]David Stutz, Matthias Hein, Bernt Schiele:
Confidence-Calibrated Adversarial Training: Towards Robust Models Generalizing Beyond the Attack Used During Training. CoRR abs/1910.06259 (2019) - [i45]Pedro Mercado, Francesco Tudisco, Matthias Hein:
Generalized Matrix Means for Semi-Supervised Learning with Multilayer Graphs. CoRR abs/1910.13951 (2019) - [i44]Maksym Andriushchenko, Francesco Croce, Nicolas Flammarion, Matthias Hein:
Square Attack: a query-efficient black-box adversarial attack via random search. CoRR abs/1912.00049 (2019) - 2018
- [j14]Maksim Lapin, Matthias Hein, Bernt Schiele:
Analysis and Optimization of Loss Functions for Multiclass, Top-k, and Multilabel Classification. IEEE Trans. Pattern Anal. Mach. Intell. 40(7): 1533-1554 (2018) - [j13]Francesco Tudisco, Pedro Mercado, Matthias Hein:
Community Detection in Networks via Nonlinear Modularity Eigenvectors. SIAM J. Appl. Math. 78(5): 2393-2419 (2018) - [c48]Pedro Mercado, Antoine Gautier, Francesco Tudisco, Matthias Hein:
The Power Mean Laplacian for Multilayer Graph Clustering. AISTATS 2018: 1828-1838 - [c47]Francesco Croce, Matthias Hein:
A Randomized Gradient-Free Attack on ReLU Networks. GCPR 2018: 215-227 - [c46]Quynh Nguyen, Matthias Hein:
The loss surface and expressivity of deep convolutional neural networks. ICLR (Workshop) 2018 - [c45]Quynh Nguyen, Matthias Hein:
Optimization Landscape and Expressivity of Deep CNNs. ICML 2018: 3727-3736 - [c44]Quynh Nguyen, Mahesh Chandra Mukkamala, Matthias Hein:
Neural Networks Should Be Wide Enough to Learn Disconnected Decision Regions. ICML 2018: 3737-3746 - [i43]Antoine Gautier, Francesco Tudisco, Matthias Hein:
A unifying Perron-Frobenius theorem for nonnegative tensors via multi-homogeneous maps. CoRR abs/1801.04215 (2018) - [i42]Quynh Nguyen, Mahesh Chandra Mukkamala, Matthias Hein:
Neural Networks Should Be Wide Enough to Learn Disconnected Decision Regions. CoRR abs/1803.00094 (2018) - [i41]Pedro Mercado, Antoine Gautier, Francesco Tudisco, Matthias Hein:
The Power Mean Laplacian for Multilayer Graph Clustering. CoRR abs/1803.00491 (2018) - [i40]Quynh Nguyen, Mahesh Chandra Mukkamala, Matthias Hein:
On the loss landscape of a class of deep neural networks with no bad local valleys. CoRR abs/1809.10749 (2018) - [i39]Francesco Croce, Maksym Andriushchenko, Matthias Hein:
Provable Robustness of ReLU networks via Maximization of Linear Regions. CoRR abs/1810.07481 (2018) - [i38]Marius Mosbach, Maksym Andriushchenko, Thomas Alexander Trost, Matthias Hein, Dietrich Klakow:
Logit Pairing Methods Can Fool Gradient-Based Attacks. CoRR abs/1810.12042 (2018) - [i37]Francesco Croce, Matthias Hein:
A randomized gradient-free attack on ReLU networks. CoRR abs/1811.11493 (2018) - [i36]David Stutz, Matthias Hein, Bernt Schiele:
Disentangling Adversarial Robustness and Generalization. CoRR abs/1812.00740 (2018) - [i35]Matthias Hein, Maksym Andriushchenko, Julian Bitterwolf:
Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problem. CoRR abs/1812.05720 (2018) - 2017
- [j12]Quynh Nguyen, Francesco Tudisco, Antoine Gautier, Matthias Hein:
An Efficient Multilinear Optimization Framework for Hypergraph Matching. IEEE Trans. Pattern Anal. Mach. Intell. 39(6): 1054-1075 (2017) - [c43]Anna Khoreva, Rodrigo Benenson, Jan Hendrik Hosang, Matthias Hein, Bernt Schiele:
Simple Does It: Weakly Supervised Instance and Semantic Segmentation. CVPR 2017: 1665-1674 - [c42]Mahesh Chandra Mukkamala, Matthias Hein:
Variants of RMSProp and Adagrad with Logarithmic Regret Bounds. ICML 2017: 2545-2553 - [c41]Quynh Nguyen, Matthias Hein:
The Loss Surface of Deep and Wide Neural Networks. ICML 2017: 2603-2612 - [c40]Matthias Hein, Maksym Andriushchenko:
Formal Guarantees on the Robustness of a Classifier against Adversarial Manipulation. NIPS 2017: 2266-2276 - [i34]Pedro Mercado, Francesco Tudisco, Matthias Hein:
Clustering Signed Networks with the Geometric Mean of Laplacians. CoRR abs/1701.00757 (2017) - [i33]Quynh Nguyen, Matthias Hein:
The loss surface of deep and wide neural networks. CoRR abs/1704.08045 (2017) - [i32]Matthias Hein, Maksym Andriushchenko:
Formal Guarantees on the Robustness of a Classifier against Adversarial Manipulation. CoRR abs/1705.08475 (2017) - [i31]Mahesh Chandra Mukkamala, Matthias Hein:
Variants of RMSProp and Adagrad with Logarithmic Regret Bounds. CoRR abs/1706.05507 (2017) - [i30]Francesco Tudisco, Pedro Mercado, Matthias Hein:
Community detection in networks via nonlinear modularity eigenvectors. CoRR abs/1708.05569 (2017) - [i29]Quynh Nguyen, Matthias Hein:
The loss surface and expressivity of deep convolutional neural networks. CoRR abs/1710.10928 (2017) - 2016
- [c39]Yongqin Xian, Zeynep Akata, Gaurav Sharma, Quynh Nguyen, Matthias Hein, Bernt Schiele:
Latent Embeddings for Zero-Shot Classification. CVPR 2016: 69-77 - [c38]Anna Khoreva, Rodrigo Benenson, Mohamed Omran, Matthias Hein, Bernt Schiele:
Weakly Supervised Object Boundaries. CVPR 2016: 183-192 - [c37]Maksim Lapin, Matthias Hein, Bernt Schiele:
Loss Functions for Top-k Error: Analysis and Insights. CVPR 2016: 1468-1477 - [c36]Anna Khoreva, Rodrigo Benenson, Fabio Galasso, Matthias Hein, Bernt Schiele:
Improved Image Boundaries for Better Video Segmentation. ECCV Workshops (3) 2016: 773-788 - [c35]Antoine Gautier, Quynh Nguyen, Matthias Hein:
Globally Optimal Training of Generalized Polynomial Neural Networks with Nonlinear Spectral Methods. NIPS 2016: 1687-1695 - [c34]Pedro Mercado, Francesco Tudisco, Matthias Hein:
Clustering Signed Networks with the Geometric Mean of Laplacians. NIPS 2016: 4421-4429 - [i28]Francesco Tudisco, Matthias Hein:
Nodal domain theorem for the graph p-Laplacian. CoRR abs/1602.05567 (2016) - [i27]Anna Khoreva, Rodrigo Benenson, Jan Hendrik Hosang, Matthias Hein, Bernt Schiele:
Weakly Supervised Semantic Labelling and Instance Segmentation. CoRR abs/1603.07485 (2016) - [i26]Yongqin Xian, Zeynep Akata, Gaurav Sharma, Quynh Nguyen, Matthias Hein, Bernt Schiele:
Latent Embeddings for Zero-shot Classification. CoRR abs/1603.08895 (2016) - [i25]Anna Khoreva, Rodrigo Benenson, Fabio Galasso, Matthias Hein, Bernt Schiele:
Improved Image Boundaries for Better Video Segmentation. CoRR abs/1605.03718 (2016) - [i24]Antoine Gautier, Quynh Nguyen, Matthias Hein:
Globally Optimal Training of Generalized Polynomial Neural Networks with Nonlinear Spectral Methods. CoRR abs/1610.09300 (2016) - [i23]Maksim Lapin, Matthias Hein, Bernt Schiele:
Analysis and Optimization of Loss Functions for Multiclass, Top-k, and Multilabel Classification. CoRR abs/1612.03663 (2016) - 2015
- [j11]Sahely Bhadra, Matthias Hein:
Correction of noisy labels via mutual consistency check. Neurocomputing 160: 34-52 (2015) - [c33]Anna Khoreva, Fabio Galasso, Matthias Hein, Bernt Schiele:
Classifier based graph construction for video segmentation. CVPR 2015: 951-960 - [c32]Quynh Nguyen Ngoc, Antoine Gautier, Matthias Hein:
A flexible tensor block coordinate ascent scheme for hypergraph matching. CVPR 2015: 5270-5278 - [c31]Maksim Lapin, Matthias Hein, Bernt Schiele:
Top-k Multiclass SVM. NIPS 2015: 325-333 - [c30]Pratik Jawanpuria, Maksim Lapin, Matthias Hein, Bernt Schiele:
Efficient Output Kernel Learning for Multiple Tasks. NIPS 2015: 1189-1197 - [c29]Martin Slawski, Ping Li, Matthias Hein:
Regularization-Free Estimation in Trace Regression with Symmetric Positive Semidefinite Matrices. NIPS 2015: 2782-2790 - [i22]Martin Slawski, Ping Li, Matthias Hein:
Regularization-free estimation in trace regression with symmetric positive semidefinite matrices. CoRR abs/1504.06305 (2015) - [i21]Quynh Nguyen Ngoc, Antoine Gautier, Matthias Hein:
A Flexible Tensor Block Coordinate Ascent Scheme for Hypergraph Matching. CoRR abs/1504.07907 (2015) - [i20]Syama Sundar Rangapuram, Pramod Kaushik Mudrakarta, Matthias Hein:
Tight Continuous Relaxation of the Balanced k-Cut Problem. CoRR abs/1505.06478 (2015) - [i19]Syama Sundar Rangapuram, Matthias Hein:
Constrained 1-Spectral Clustering. CoRR abs/1505.06485 (2015) - [i18]Syama Sundar Rangapuram, Thomas Bühler, Matthias Hein:
Towards Realistic Team Formation in Social Networks based on Densest Subgraphs. CoRR abs/1505.06661 (2015) - [i17]Anastasia Podosinnikova, Simon Setzer, Matthias Hein:
Robust PCA: Optimization of the Robust Reconstruction Error over the Stiefel Manifold. CoRR abs/1506.00323 (2015) - [i16]Quynh Nguyen, Francesco Tudisco, Antoine Gautier, Matthias Hein:
An Efficient Multilinear Optimization Framework for Hypergraph Matching. CoRR abs/1511.02667 (2015) - [i15]Pratik Jawanpuria, Maksim Lapin, Matthias Hein, Bernt Schiele:
Efficient Output Kernel Learning for Multiple Tasks. CoRR abs/1511.05706 (2015) - [i14]Maksim Lapin, Matthias Hein, Bernt Schiele:
Top-k Multiclass SVM. CoRR abs/1511.06683 (2015) - [i13]Anna Khoreva, Rodrigo Benenson, Mohamed Omran, Matthias Hein, Bernt Schiele:
Weakly Supervised Object Boundaries. CoRR abs/1511.07803 (2015) - [i12]Maksim Lapin, Matthias Hein, Bernt Schiele:
Loss Functions for Top-k Error: Analysis and Insights. CoRR abs/1512.00486 (2015) - [i11]Matthias Hein, Gábor Lugosi, Lorenzo Rosasco:
Mathematical and Computational Foundations of Learning Theory (Dagstuhl Seminar 15361). Dagstuhl Reports 5(8): 54-0 (2015) - 2014
- [j10]Ulrike von Luxburg, Agnes Radl, Matthias Hein:
Hitting and commute times in large random neighborhood graphs. J. Mach. Learn. Res. 15(1): 1751-1798 (2014) - [j9]Maksim Lapin, Matthias Hein, Bernt Schiele:
Learning using privileged information: SV M+ and weighted SVM. Neural Networks 53: 95-108 (2014) - [c28]Maksim Lapin, Bernt Schiele, Matthias Hein:
Scalable Multitask Representation Learning for Scene Classification. CVPR 2014: 1434-1441 - [c27]Anastasia Podosinnikova, Simon Setzer, Matthias Hein:
Robust PCA: Optimization of the Robust Reconstruction Error Over the Stiefel Manifold. GCPR 2014: 121-131 - [c26]Anna Khoreva, Fabio Galasso, Matthias Hein, Bernt Schiele:
Learning Must-Link Constraints for Video Segmentation Based on Spectral Clustering. GCPR 2014: 701-712 - [c25]Syama Sundar Rangapuram, Pramod Kaushik Mudrakarta, Matthias Hein:
Tight Continuous Relaxation of the Balanced k-Cut Problem. NIPS 2014: 3131-3139 - [i10]Martin Slawski, Matthias Hein, Pavlo Lutsik:
Matrix factorization with Binary Components. CoRR abs/1401.6024 (2014) - 2013
- [c24]Thomas Bühler, Syama Sundar Rangapuram, Simon Setzer, Matthias Hein:
Constrained fractional set programs and their application in local clustering and community detection. ICML (1) 2013: 624-632 - [c23]Matthias Hein, Simon Setzer, Leonardo Jost, Syama Sundar Rangapuram:
The Total Variation on Hypergraphs - Learning on Hypergraphs Revisited. NIPS 2013: 2427-2435 - [c22]Martin Slawski, Matthias Hein, Pavlo Lutsik:
Matrix factorization with binary components. NIPS 2013: 3210-3218 - [c21]Syama Sundar Rangapuram, Thomas Bühler, Matthias Hein:
Towards realistic team formation in social networks based on densest subgraphs. WWW 2013: 1077-1088 - [e1]Joachim Weickert, Matthias Hein, Bernt Schiele:
Pattern Recognition - 35th German Conference, GCPR 2013, Saarbrücken, Germany, September 3-6, 2013. Proceedings. Lecture Notes in Computer Science 8142, Springer 2013, ISBN 978-3-642-40601-0 [contents] - [i9]Maksim Lapin, Matthias Hein, Bernt Schiele:
Learning Using Privileged Information: SVM+ and Weighted SVM. CoRR abs/1306.3161 (2013) - [i8]Thomas Bühler, Syama Sundar Rangapuram, Simon Setzer, Matthias Hein:
Constrained fractional set programs and their application in local clustering and community detection. CoRR abs/1306.3409 (2013) - [i7]Matthias Hein, Simon Setzer, Leonardo Jost, Syama Sundar Rangapuram:
The Total Variation on Hypergraphs - Learning on Hypergraphs Revisited. CoRR abs/1312.5179 (2013) - [i6]Leonardo Jost, Simon Setzer, Matthias Hein:
Nonlinear Eigenproblems in Data Analysis - Balanced Graph Cuts and the RatioDCA-Prox. CoRR abs/1312.5192 (2013) - 2012
- [j8]Martin Slawski, Rene Hussong, Andreas Tholey, Thomas Jakoby, Barbara Gregorius, Andreas Hildebrandt, Matthias Hein:
Isotope pattern deconvolution for peptide mass spectrometry by non-negative least squares/least absolute deviation template matching. BMC Bioinform. 13: 291 (2012) - [c20]Syama Sundar Rangapuram, Matthias Hein:
Constrained 1-Spectral Clustering. AISTATS 2012: 1143-1151 - 2011
- [c19]Martin Slawski, Matthias Hein:
Sparse recovery by thresholded non-negative least squares. NIPS 2011: 1926-1934 - [c18]Matthias Hein, Simon Setzer:
Beyond Spectral Clustering - Tight Relaxations of Balanced Graph Cuts. NIPS 2011: 2366-2374 - [i5]Markus Maier, Ulrike von Luxburg, Matthias Hein:
How the result of graph clustering methods depends on the construction of the graph. CoRR abs/1102.2075 (2011) - [i4]Matthias Hein, Gábor Lugosi, Lorenzo Rosasco, Steve Smale:
Mathematical and Computational Foundations of Learning Theory (Dagstuhl Seminar 11291). Dagstuhl Reports 1(7): 53-69 (2011) - 2010
- [j7]Florian Steinke, Matthias Hein, Bernhard Schölkopf:
Nonparametric Regression between General Riemannian Manifolds. SIAM J. Imaging Sci. 3(3): 527-563 (2010) - [c17]Matthias Hein, Thomas Bühler:
An Inverse Power Method for Nonlinear Eigenproblems with Applications in 1-Spectral Clustering and Sparse PCA. NIPS 2010: 847-855 - [c16]Ulrike von Luxburg, Agnes Radl, Matthias Hein:
Getting lost in space: Large sample analysis of the resistance distance. NIPS 2010: 2622-2630 - [i3]Ulrike von Luxburg, Agnes Radl, Matthias Hein:
Hitting times, commute distances and the spectral gap for large random geometric graphs. CoRR abs/1003.1266 (2010) - [i2]Matthias Hein, Thomas Bühler:
An Inverse Power Method for Nonlinear Eigenproblems with Applications in 1-Spectral Clustering and Sparse PCA. CoRR abs/1012.0774 (2010)
2000 – 2009
- 2009
- [j6]Andreas Keller, Nicole Ludwig, Sabrina Heisel, Petra Leidinger, Claudia Andres, Wolf-Ingo Steudel, Hanno Huwer, Bernhard Burgeth, Matthias Hein, Joachim Weickert, Eckart Meese, Hans-Peter Lenhof:
Large-scale antibody profiling of human blood sera: The future of molecular diagnosis. Inform. Spektrum 32(4): 332-338 (2009) - [j5]Markus Maier, Matthias Hein, Ulrike von Luxburg:
Optimal construction of k-nearest-neighbor graphs for identifying noisy clusters. Theor. Comput. Sci. 410(19): 1749-1764 (2009) - [c15]Thomas Bühler, Matthias Hein:
Spectral clustering based on the graph p-Laplacian. ICML 2009: 81-88 - [c14]Matthias Hein:
Robust Nonparametric Regression with Metric-Space Valued Output. NIPS 2009: 718-726 - [c13]Kwang In Kim, Florian Steinke, Matthias Hein:
Semi-supervised Regression using Hessian energy with an application to semi-supervised dimensionality reduction. NIPS 2009: 979-987 - 2008
- [j4]Florian Steinke, Matthias Hein, Jan Peters, Bernhard Schölkopf:
Manifold-valued Thin-Plate Splines with Applications in Computer Graphics. Comput. Graph. Forum 27(2): 437-448 (2008) - [j3]Piotr Didyk, Rafal Mantiuk, Matthias Hein, Hans-Peter Seidel:
Enhancement of Bright Video Features for HDR Displays. Comput. Graph. Forum 27(4): 1265-1274 (2008) - [c12]Markus Maier, Ulrike von Luxburg, Matthias Hein:
Influence of graph construction on graph-based clustering measures. NIPS 2008: 1025-1032 - [c11]Florian Steinke, Matthias Hein:
Non-parametric Regression Between Manifolds. NIPS 2008: 1561-1568 - 2007
- [j2]Matthias Hein, Jean-Yves Audibert, Ulrike von Luxburg:
Graph Laplacians and their Convergence on Random Neighborhood Graphs. J. Mach. Learn. Res. 8: 1325-1368 (2007) - [c10]Matthias Hein, Markus Maier:
Manifold Denoising as Preprocessing for Finding Natural Representations of Data. AAAI 2007: 1646-1649 - [c9]Markus Maier, Matthias Hein, Ulrike von Luxburg:
Cluster Identification in Nearest-Neighbor Graphs. ALT 2007: 196-210 - 2006
- [c8]Matthias Hein:
Uniform Convergence of Adaptive Graph-Based Regularization. COLT 2006: 50-64 - [c7]Matthias Hein, Markus Maier:
Manifold Denoising. NIPS 2006: 561-568 - [i1]Matthias Hein, Jean-Yves Audibert, Ulrike von Luxburg:
Graph Laplacians and their convergence on random neighborhood graphs. CoRR abs/math/0608522 (2006) - 2005
- [b1]Matthias Hein:
Geometrical aspects of statistical learning theory. Darmstadt University of Technology, Germany, 2005, pp. 1-153 - [j1]Matthias Hein, Olivier Bousquet, Bernhard Schölkopf:
Maximal margin classification for metric spaces. J. Comput. Syst. Sci. 71(3): 333-359 (2005) - [c6]Matthias Hein, Olivier Bousquet:
Hilbertian Metrics and Positive Definite Kernels on Probability Measures. AISTATS 2005: 136-143 - [c5]Matthias Hein, Jean-Yves Audibert, Ulrike von Luxburg:
From Graphs to Manifolds - Weak and Strong Pointwise Consistency of Graph Laplacians. COLT 2005: 470-485 - [c4]Matthias Hein, Jean-Yves Audibert:
Intrinsic dimensionality estimation of submanifolds in Rd. ICML 2005: 289-296 - 2004
- [c3]Matthias Hein, Thomas Navin Lal, Olivier Bousquet:
Hilbertian Metrics on Probability Measures and Their Application in SVM?s. DAGM-Symposium 2004: 270-277 - 2003
- [c2]Matthias Hein, Olivier Bousquet:
Maximal Margin Classification for Metric Spaces. COLT 2003: 72-86 - [c1]Olivier Bousquet, Olivier Chapelle, Matthias Hein:
Measure Based Regularization. NIPS 2003: 1221-1228
Coauthor Index
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
Unpaywalled article links
Add open access links from 
to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the 
of the Internet Archive (if available).
Privacy notice: By enabling the option above, your browser will contact the API of archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from 
, 
, and 
to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
OpenAlex data
Load additional information about publications from 
.
Privacy notice: By enabling the option above, your browser will contact the API of openalex.org to load additional information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the information given by OpenAlex.
last updated on 2025-01-21 21:23 CET by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by:
