Matthias Hein - RankMe

246 papers A* 55A 6B 2Journal 138Unranked 43

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	On the Out-of-Distribution Generalization of Reasoning in Multimodal LLMs for Simple Visual Planning Tasks. CoRR Yannic Neuhaus, Nicolas Flammarion, Matthias Hein, Francesco Croce
2026	J	`jnl`	Toxicity Assessment in Preclinical Histopathology via Class-Aware Mahalanobis Distance for Known and Novel Anomalies. CoRR Olga Graf, Dhrupal Patel, Peter Groß, Charlotte Lempp, Matthias Hein, Fabian Heinemann
2026	J	`jnl`	Visual Memory Injection Attacks for Multi-Turn Conversations. CoRR Christian Schlarmann, Matthias Hein
2025	J	`jnl`	A Definition of AGI. CoRR Dan Hendrycks, Dawn Song, Christian Szegedy, Honglak Lee, Yarin Gal, Erik Brynjolfsson, Sharon Li, Andy Zou, Lionel Levine, Bo Han, Jie Fu, Ziwei Liu, Jinwoo Shin, Kimin Lee, Mantas Mazeika, Long Phan, George Ingebretsen, Adam Khoja, Cihang Xie, Olawale Salaudeen, Matthias Hein, Kevin Zhao, Alexander Pan, David Duvenaud, Bo Li, Steve Omohundro, Gabriel Alfour, Max Tegmark, Kevin McGrew, Gary Marcus, Jaan Tallinn, Eric Schmidt, Yoshua Bengio
2025	J	`jnl`	Advancing Compositional Awareness in CLIP with Efficient Fine-Tuning. CoRR Amit Peleg, Naman Deep Singh, Matthias Hein
2025	—	`conf`	Adversarially Robust CLIP Models Can Induce Better (Robust) Perceptual Metrics. SaTML Francesco Croce, Christian Schlarmann, Naman Deep Singh, Matthias Hein
2025	J	`jnl`	Adversarially Robust CLIP Models Can Induce Better (Robust) Perceptual Metrics. CoRR Francesco Croce, Christian Schlarmann, Naman Deep Singh, Matthias Hein
2025	A*	`conf`	An Interpretable N-gram Perplexity Threat Model for Large Language Model Jailbreaks. ICML Valentyn Boreiko, Alexander Panfilov, Václav Vorácek, Matthias Hein, Jonas Geiping
2025	J	`jnl`	DASH: Detection and Assessment of Systematic Hallucinations of VLMs. CoRR Maximilian Augustin, Yannic Neuhaus, Matthias Hein
2025	J	`jnl`	FuseLIP: Multimodal Embeddings via Early Fusion of Discrete Tokens. CoRR Christian Schlarmann, Francesco Croce, Nicolas Flammarion, Matthias Hein
2025	J	`jnl`	Improving Knowledge Distillation Under Unknown Covariate Shift Through Confidence-Guided Data Augmentation. CoRR Niclas Popp, Kevin Alexander Laube, Matthias Hein, Lukas Schott
2025	A*	`conf`	Mahalanobis++: Improving OOD Detection via Feature Normalization. ICML Maximilian Müller, Matthias Hein
2025	J	`jnl`	Mahalanobis++: Improving OOD Detection via Feature Normalization. CoRR Maximilian Müller, Matthias Hein
2025	—	`conf`	Mind the Detail: Uncovering Clinically Relevant Image Details in Accelerated MRI with Semantically Diverse Reconstructions. MICCAI (2) Jan Nikolas Morshuis, Christian Schlarmann, Thomas Küstner, Christian F. Baumgartner, Matthias Hein
2025	J	`jnl`	Mind the Detail: Uncovering Clinically Relevant Image Details in Accelerated MRI with Semantically Diverse Reconstructions. CoRR Jan Nikolas Morshuis, Christian Schlarmann, Thomas Küstner, Christian F. Baumgartner, Matthias Hein
2025	J	`jnl`	RePOPE: Impact of Annotation Errors on the POPE Benchmark. CoRR Yannic Neuhaus, Matthias Hein
2025	J	`jnl`	Robustness in Both Domains: CLIP Needs a Robust Text Encoder. CoRR Elías Abad-Rocamora, Christian Schlarmann, Naman Deep Singh, Yongtao Wu, Matthias Hein, Volkan Cevher
2025	—	`conf`	Segmenting Brain Regions in Low Field Pediatric Brain MR Images Using (Symmetric) NnU-Net ResEnc. LISA@MICCAI Jan Nikolas Morshuis, Matthias Hein, Christian F. Baumgartner
2025	J	`jnl`	Understanding Benefits and Pitfalls of Current Methods for the Segmentation of Undersampled MRI Data. CoRR Jan Nikolas Morshuis, Matthias Hein, Christian F. Baumgartner
2025	J	`jnl`	Unlearning That Lasts: Utility-Preserving, Robust, and Almost Irreversible Forgetting in LLMs. CoRR Naman Deep Singh, Maximilian Müller, Francesco Croce, Matthias Hein
2024	J	`jnl`	A Realistic Threat Model for Large Language Model Jailbreaks. CoRR Valentyn Boreiko, Alexander Panfilov, Václav Vorácek, Matthias Hein, Jonas Geiping
2024	A*	`conf`	Bias of Stochastic Gradient Descent or the Architecture: Disentangling the Effects of Overparameterization of Neural Networks. ICML Amit Peleg, Matthias Hein
2024	J	`jnl`	Bias of Stochastic Gradient Descent or the Architecture: Disentangling the Effects of Overparameterization of Neural Networks. CoRR Amit Peleg, Matthias Hein
2024	A*	`conf`	DiG-IN: Diffusion Guidance for Investigating Networks - Uncovering Classifier Differences, Neuron Visualisations, and Visual Counterfactual Explanations. CVPR Maximilian Augustin, Yannic Neuhaus, Matthias Hein
2024	J	`jnl`	Feature Distillation Improves Zero-Shot Transfer from Synthetic Images. Trans. Mach. Learn. Res. Niclas Popp, Jan Hendrik Metzen, Matthias Hein
2024	J	`jnl`	How to train your ViT for OOD Detection. CoRR Maximilian Müller, Matthias Hein
2024	J	`jnl`	Identification of Fine-grained Systematic Errors via Controlled Scene Generation. CoRR Valentyn Boreiko, Matthias Hein, Jan Hendrik Metzen
2024	J	`jnl`	LoGex: Improved tail detection of extremely rare histopathology classes via guided diffusion. CoRR Maximilian Müller, Matthias Hein
2024	J	`jnl`	Object-Focused Data Selection for Dense Prediction Tasks. CoRR Niclas Popp, Dan Zhang, Jan Hendrik Metzen, Matthias Hein, Lukas Schott
2024	J	`jnl`	Perturb and Recover: Fine-tuning for Effective Backdoor Removal from CLIP. CoRR Naman Deep Singh, Francesco Croce, Matthias Hein
2024	A*	`conf`	Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models. ICML Christian Schlarmann, Naman Deep Singh, Francesco Croce, Matthias Hein
2024	J	`jnl`	Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models. CoRR Christian Schlarmann, Naman Deep Singh, Francesco Croce, Matthias Hein
2024	—	`conf`	Segment (Almost) Nothing: Prompt-Agnostic Adversarial Attacks on Segmentation Models. SaTML Francesco Croce, Matthias Hein
2024	—	`conf`	Segmentation-Guided MRI Reconstruction for Meaningfully Diverse Reconstructions. DGM4MICCAI@MICCAI Jan Nikolas Morshuis, Matthias Hein, Christian F. Baumgartner
2024	J	`jnl`	Segmentation-guided MRI reconstruction for meaningfully diverse reconstructions. CoRR Jan Nikolas Morshuis, Matthias Hein, Christian F. Baumgartner
2024	—	`conf`	Towards Reliable Evaluation and Fast Training of Robust Semantic Segmentation Models. ECCV (79) Francesco Croce, Naman D. Singh, Matthias Hein
2024	J	`jnl`	Zero-Shot Distillation for Image Encoders: How to Make Effective Use of Synthetic Data. CoRR Niclas Popp, Jan Hendrik Metzen, Matthias Hein
2023	A*	`conf`	A Modern Look at the Relationship between Sharpness and Generalization. ICML Maksym Andriushchenko, Francesco Croce, Maximilian Müller, Matthias Hein, Nicolas Flammarion
2023	J	`jnl`	A modern look at the relationship between sharpness and generalization. CoRR Maksym Andriushchenko, Francesco Croce, Maximilian Müller, Matthias Hein, Nicolas Flammarion
2023	J	`jnl`	Analyzing and Explaining Image Classifiers via Diffusion Guidance. CoRR Maximilian Augustin, Yannic Neuhaus, Matthias Hein
2023	A*	`conf`	Certified Defences Against Adversarial Patch Attacks on Semantic Segmentation. ICLR Maksym Yatsura, Kaspar Sakmann, N. Grace Hua, Matthias Hein, Jan Hendrik Metzen
2023	J	`jnl`	Generating Realistic Counterfactuals for Retinal Fundus and OCT Images using Diffusion Models. CoRR Indu Ilanchezian, Valentyn Boreiko, Laura Kühlewein, Ziwei Huang, Murat Seçkin Ayhan, Matthias Hein, Lisa M. Koch, Philipp Berens
2023	—	`conf`	Identifying Systematic Errors in Object Detectors with the SCROD Pipeline. ICCV (Workshops) Valentyn Boreiko, Matthias Hein, Jan Hendrik Metzen
2023	J	`jnl`	Identifying Systematic Errors in Object Detectors with the SCROD Pipeline. CoRR Valentyn Boreiko, Matthias Hein, Jan Hendrik Metzen
2023	A*	`conf`	Improving l1-Certified Robustness via Randomized Smoothing by Leveraging Box Constraints. ICML Václav Vorácek, Matthias Hein
2023	A*	`conf`	In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluation. ICML Julian Bitterwolf, Maximilian Müller, Matthias Hein
2023	J	`jnl`	In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluation. CoRR Julian Bitterwolf, Maximilian Müller, Matthias Hein
2023	J	`jnl`	Nonlinear Perron-Frobenius Theorems for Nonnegative Tensors. SIAM Rev. Antoine Gautier, Francesco Tudisco, Matthias Hein
2023	A*	`conf`	Normalization Layers Are All That Sharpness-Aware Minimization Needs. NeurIPS Maximilian Müller, Tiffany Vlaar, David Rolnick, Matthias Hein
2023	J	`jnl`	Normalization Layers Are All That Sharpness-Aware Minimization Needs. CoRR Maximilian Müller, Tiffany Vlaar, David Rolnick, Matthias Hein
2023	—	`conf`	On the Adversarial Robustness of Multi-Modal Foundation Models. ICCV (Workshops) Christian Schlarmann, Matthias Hein
2023	J	`jnl`	On the Adversarial Robustness of Multi-Modal Foundation Models. CoRR Christian Schlarmann, Matthias Hein
2023	J	`jnl`	Random and Adversarial Bit Error Robustness: Energy-Efficient and Secure DNN Accelerators. IEEE Trans. Pattern Anal. Mach. Intell. David Stutz, Nandhini Chandramoorthy, Matthias Hein, Bernt Schiele
2023	A*	`conf`	Revisiting Adversarial Training for ImageNet: Architectures, Training and Generalization across Threat Models. NeurIPS Naman Deep Singh, Francesco Croce, Matthias Hein
2023	J	`jnl`	Revisiting Adversarial Training for ImageNet: Architectures, Training and Generalization across Threat Models. CoRR Naman D. Singh, Francesco Croce, Matthias Hein
2023	J	`jnl`	Robust Semantic Segmentation: Strong Adversarial Attacks and Fast Training of Robust Models. CoRR Francesco Croce, Naman D. Singh, Matthias Hein
2023	J	`jnl`	Segment (Almost) Nothing: Prompt-Agnostic Adversarial Attacks on Segmentation Models. CoRR Francesco Croce, Matthias Hein
2023	A*	`conf`	Sound Randomized Smoothing in Floating-Point Arithmetic. ICLR Václav Vorácek, Matthias Hein
2023	A*	`conf`	Spurious Features Everywhere - Large-Scale Detection of Harmful Spurious Features in ImageNet. ICCV Yannic Neuhaus, Maximilian Augustin, Valentyn Boreiko, Matthias Hein
2022	A*	`conf`	Adversarial Robustness against Multiple and Single l ICML Francesco Croce, Matthias Hein
2022	—	`conf`	Adversarial Robustness of MR Image Reconstruction Under Realistic Perturbations. MLMIR@MICCAI Jan Nikolas Morshuis, Sergios Gatidis, Matthias Hein, Christian F. Baumgartner
2022	J	`jnl`	Adversarial Robustness of MR Image Reconstruction under Realistic Perturbations. CoRR Jan Nikolas Morshuis, Sergios Gatidis, Matthias Hein, Christian F. Baumgartner
2022	A	`conf`	Being a Bit Frequentist Improves Bayesian Neural Networks. AISTATS Agustinus Kristiadi, Matthias Hein, Philipp Hennig
2022	A*	`conf`	Breaking Down Out-of-Distribution Detection: Many Methods Based on OOD Training Data Estimate a Combination of the Same Core Quantities. ICML Julian Bitterwolf, Alexander Meinke, Maximilian Augustin, Matthias Hein
2022	J	`jnl`	Breaking Down Out-of-Distribution Detection: Many Methods Based on OOD Training Data Estimate a Combination of the Same Core Quantities. CoRR Julian Bitterwolf, Alexander Meinke, Maximilian Augustin, Matthias Hein
2022	J	`jnl`	Certified Defences Against Adversarial Patch Attacks on Semantic Segmentation. CoRR Maksym Yatsura, Kaspar Sakmann, N. Grace Hua, Matthias Hein, Jan Hendrik Metzen
2022	A*	`conf`	Diffusion Visual Counterfactual Explanations. NeurIPS Maximilian Augustin, Valentyn Boreiko, Francesco Croce, Matthias Hein
2022	J	`jnl`	Diffusion Visual Counterfactual Explanations. CoRR Maximilian Augustin, Valentyn Boreiko, Francesco Croce, Matthias Hein
2022	A*	`conf`	Evaluating the Adversarial Robustness of Adaptive Test-time Defenses. ICML Francesco Croce, Sven Gowal, Thomas Brunner, Evan Shelhamer, Matthias Hein, A. Taylan Cemgil
2022	J	`jnl`	Evaluating the Adversarial Robustness of Adaptive Test-time Defenses. CoRR Francesco Croce, Sven Gowal, Thomas Brunner, Evan Shelhamer, Matthias Hein, A. Taylan Cemgil
2022	B	`conf`	Neural Network Heuristic Functions: Taking Confidence into Account. SOCS Daniel Heller, Patrick Ferber, Julian Bitterwolf, Matthias Hein, Jörg Hoffmann
2022	J	`jnl`	On the interplay of adversarial robustness and architecture components: patches, convolution and attention. CoRR Francesco Croce, Matthias Hein
2022	A*	`conf`	Provably Adversarially Robust Detection of Out-of-Distribution Data (Almost) for Free. NeurIPS Alexander Meinke, Julian Bitterwolf, Matthias Hein
2022	A*	`conf`	Provably Adversarially Robust Nearest Prototype Classifiers. ICML Václav Vorácek, Matthias Hein
2022	J	`jnl`	Provably Adversarially Robust Nearest Prototype Classifiers. CoRR Václav Vorácek, Matthias Hein
2022	J	`jnl`	Sound Randomized Smoothing in Floating-Point Arithmetics. CoRR Václav Vorácek, Matthias Hein
2022	—	`conf`	Sparse Visual Counterfactual Explanations in Image Space. GCPR Valentyn Boreiko, Maximilian Augustin, Francesco Croce, Philipp Berens, Matthias Hein
2022	J	`jnl`	Sparse Visual Counterfactual Explanations in Image Space. CoRR Valentyn Boreiko, Maximilian Augustin, Francesco Croce, Philipp Berens, Matthias Hein
2022	A*	`conf`	Sparse-RS: A Versatile Framework for Query-Efficient Sparse Black-Box Adversarial Attacks. AAAI Francesco Croce, Maksym Andriushchenko, Naman D. Singh, Nicolas Flammarion, Matthias Hein
2022	J	`jnl`	Spurious Features Everywhere - Large-Scale Detection of Harmful Spurious Features in ImageNet. CoRR Yannic Neuhaus, Maximilian Augustin, Valentyn Boreiko, Matthias Hein
2022	—	`conf`	Visual Explanations for the Detection of Diabetic Retinopathy from Retinal Fundus Images. MICCAI (2) Valentyn Boreiko, Indu Ilanchezian, Murat Seçkin Ayhan, Sarah Müller, Lisa M. Koch, Hanna Faber, Philipp Berens, Matthias Hein
2021	J	`jnl`	Adversarial robustness against multiple l CoRR Francesco Croce, Matthias Hein
2021	A*	`conf`	An Infinite-Feature Extension for Bayesian ReLU Nets That Fixes Their Asymptotic Overconfidence. NeurIPS Agustinus Kristiadi, Matthias Hein, Philipp Hennig
2021	J	`jnl`	Being a Bit Frequentist Improves Bayesian Neural Networks. CoRR Agustinus Kristiadi, Matthias Hein, Philipp Hennig
2021	—	`conf`	Bit Error Robustness for Energy-Efficient DNN Accelerators. MLSys David Stutz, Nandhini Chandramoorthy, Matthias Hein, Bernt Schiele
2021	A	`conf`	Learnable uncertainty under Laplace approximations. UAI Agustinus Kristiadi, Matthias Hein, Philipp Hennig
2021	A*	`conf`	Meta-Learning the Search Distribution of Black-Box Random Search Based Adversarial Attacks. NeurIPS Maksym Yatsura, Jan Hendrik Metzen, Matthias Hein
2021	J	`jnl`	Meta-Learning the Search Distribution of Black-Box Random Search Based Adversarial Attacks. CoRR Maksym Yatsura, Jan Hendrik Metzen, Matthias Hein
2021	A*	`conf`	Mind the Box: l ICML Francesco Croce, Matthias Hein
2021	J	`jnl`	Mind the box: l CoRR Francesco Croce, Matthias Hein
2021	J	`jnl`	Provably Robust Detection of Out-of-distribution Data (almost) for free. CoRR Alexander Meinke, Julian Bitterwolf, Matthias Hein
2021	J	`jnl`	Random and Adversarial Bit Error Robustness: Energy-Efficient and Secure DNN Accelerators. CoRR David Stutz, Nandhini Chandramoorthy, Matthias Hein, Bernt Schiele
2021	A*	`conf`	Relating Adversarially Robust Generalization to Flat Minima. ICCV David Stutz, Matthias Hein, Bernt Schiele
2021	J	`jnl`	Relating Adversarially Robust Generalization to Flat Minima. CoRR David Stutz, Matthias Hein, Bernt Schiele
2021	—	`conf`	RobustBench: a standardized adversarial robustness benchmark. NeurIPS Datasets and Benchmarks Francesco Croce, Maksym Andriushchenko, Vikash Sehwag, Edoardo Debenedetti, Nicolas Flammarion, Mung Chiang, Prateek Mittal, Matthias Hein
2021	J	`jnl`	The Global Convergence of the Nonlinear Power Method for Mixed-Subordinate Matrix Norms. J. Sci. Comput. Antoine Gautier, Matthias Hein, Francesco Tudisco
2020	—	`conf`	Adversarial Robustness on In- and Out-Distribution Improves Explainability. ECCV (26) Maximilian Augustin, Alexander Meinke, Matthias Hein
2020	J	`jnl`	Adversarial Robustness on In- and Out-Distribution Improves Explainability. CoRR Maximilian Augustin, Alexander Meinke, Matthias Hein
2020	A*	`conf`	Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networks. ICML Agustinus Kristiadi, Matthias Hein, Philipp Hennig
2020	J	`jnl`	Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networks. CoRR Agustinus Kristiadi, Matthias Hein, Philipp Hennig
2020	A*	`conf`	Certifiably Adversarially Robust Detection of Out-of-Distribution Data. NeurIPS Julian Bitterwolf, Alexander Meinke, Matthias Hein
2020	J	`jnl`	Computing the norm of nonnegative matrices and the log-Sobolev constant of Markov chains. CoRR Antoine Gautier, Matthias Hein, Francesco Tudisco
2020	A*	`conf`	Confidence-Calibrated Adversarial Training: Generalizing to Unseen Attacks. ICML David Stutz, Matthias Hein, Bernt Schiele
2020	J	`jnl`	Error Estimates for Spectral Convergence of the Graph Laplacian on Random Geometric Graphs Toward the Laplace-Beltrami Operator. Found. Comput. Math. Nicolás García Trillos, Moritz Gerlach, Matthias Hein, Dejan Slepcev
2020	J	`jnl`	Fixing Asymptotic Uncertainty of Bayesian Neural Networks with Infinite ReLU Features. CoRR Agustinus Kristiadi, Matthias Hein, Philipp Hennig
2020	J	`jnl`	Learnable Uncertainty under Laplace Approximations. CoRR Agustinus Kristiadi, Matthias Hein, Philipp Hennig
2020	A*	`conf`	Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attack. ICML Francesco Croce, Matthias Hein
2020	J	`jnl`	On Mitigating Random and Adversarial Bit Errors. CoRR David Stutz, Nandhini Chandramoorthy, Matthias Hein, Bernt Schiele
2020	J	`jnl`	Out-distribution aware Self-training in an Open World Setting. CoRR Maximilian Augustin, Matthias Hein
2020	J	`jnl`	Provable Worst Case Guarantees for the Detection of Out-of-Distribution Data. CoRR Julian Bitterwolf, Alexander Meinke, Matthias Hein
2020	A*	`conf`	Provable robustness against all adversarial $l_p$-perturbations for $p\geq 1$. ICLR Francesco Croce, Matthias Hein
2020	A*	`conf`	Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks. ICML Francesco Croce, Matthias Hein
2020	J	`jnl`	Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks. CoRR Francesco Croce, Matthias Hein
2020	J	`jnl`	RobustBench: a standardized adversarial robustness benchmark. CoRR Francesco Croce, Maksym Andriushchenko, Vikash Sehwag, Nicolas Flammarion, Mung Chiang, Prateek Mittal, Matthias Hein
2020	J	`jnl`	Scaling up the Randomized Gradient-Free Adversarial Attack Reveals Overestimation of Robustness Using Established Attacks. Int. J. Comput. Vis. Francesco Croce, Jonas Rauber, Matthias Hein
2020	J	`jnl`	Sparse-RS: a versatile framework for query-efficient sparse black-box adversarial attacks. CoRR Francesco Croce, Maksym Andriushchenko, Naman D. Singh, Nicolas Flammarion, Matthias Hein
2020	—	`conf`	Square Attack: A Query-Efficient Black-Box Adversarial Attack via Random Search. ECCV (23) Maksym Andriushchenko, Francesco Croce, Nicolas Flammarion, Matthias Hein
2020	A*	`conf`	Towards neural networks that provably know when they don't know. ICLR Alexander Meinke, Matthias Hein
2019	J	`jnl`	A Unifying Perron-Frobenius Theorem for Nonnegative Tensors via Multihomogeneous Maps. SIAM J. Matrix Anal. Appl. Antoine Gautier, Francesco Tudisco, Matthias Hein
2019	J	`jnl`	Confidence-Calibrated Adversarial Training: Towards Robust Models Generalizing Beyond the Attack Used During Training. CoRR David Stutz, Matthias Hein, Bernt Schiele
2019	A*	`conf`	Disentangling Adversarial Robustness and Generalization. CVPR David Stutz, Matthias Hein, Bernt Schiele
2019	A*	`conf`	Generalized Matrix Means for Semi-Supervised Learning with Multilayer Graphs. NeurIPS Pedro Mercado, Francesco Tudisco, Matthias Hein
2019	J	`jnl`	Generalized Matrix Means for Semi-Supervised Learning with Multilayer Graphs. CoRR Pedro Mercado, Francesco Tudisco, Matthias Hein
2019	J	`jnl`	Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attack. CoRR Francesco Croce, Matthias Hein
2019	—	`conf`	On the loss landscape of a class of deep neural networks with no bad local valleys. ICLR (Poster) Quynh Nguyen, Mahesh Chandra Mukkamala, Matthias Hein
2019	A	`conf`	Provable Robustness of ReLU networks via Maximization of Linear Regions. AISTATS Francesco Croce, Maksym Andriushchenko, Matthias Hein
2019	J	`jnl`	Provable robustness against all adversarial l CoRR Francesco Croce, Matthias Hein
2019	J	`jnl`	Provably Robust Boosted Decision Stumps and Trees against Adversarial Attacks. CoRR Maksym Andriushchenko, Matthias Hein
2019	A*	`conf`	Provably robust boosted decision stumps and trees against adversarial attacks. NeurIPS Maksym Andriushchenko, Matthias Hein
2019	J	`jnl`	Scaling up the randomized gradient-free adversarial attack reveals overestimation of robustness using established attacks. CoRR Francesco Croce, Jonas Rauber, Matthias Hein
2019	A*	`conf`	Sparse and Imperceivable Adversarial Attacks. ICCV Francesco Croce, Matthias Hein
2019	J	`jnl`	Sparse and Imperceivable Adversarial Attacks. CoRR Francesco Croce, Matthias Hein
2019	A*	`conf`	Spectral Clustering of Signed Graphs via Matrix Power Means. ICML Pedro Mercado, Francesco Tudisco, Matthias Hein
2019	J	`jnl`	Spectral Clustering of Signed Graphs via Matrix Power Means. CoRR Pedro Mercado, Francesco Tudisco, Matthias Hein
2019	J	`jnl`	Square Attack: a query-efficient black-box adversarial attack via random search. CoRR Maksym Andriushchenko, Francesco Croce, Nicolas Flammarion, Matthias Hein
2019	J	`jnl`	The Perron-Frobenius Theorem for Multihomogeneous Mappings. SIAM J. Matrix Anal. Appl. Antoine Gautier, Francesco Tudisco, Matthias Hein
2019	J	`jnl`	Towards neural networks that provably know when they don't know. CoRR Alexander Meinke, Matthias Hein
2019	A*	`conf`	Why ReLU Networks Yield High-Confidence Predictions Far Away From the Training Data and How to Mitigate the Problem. CVPR Matthias Hein, Maksym Andriushchenko, Julian Bitterwolf
2019	—	`conf`	Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problem. CVPR Workshops Matthias Hein, Maksym Andriushchenko, Julian Bitterwolf
2018	—	`conf`	A Randomized Gradient-Free Attack on ReLU Networks. GCPR Francesco Croce, Matthias Hein
2018	J	`jnl`	A randomized gradient-free attack on ReLU networks. CoRR Francesco Croce, Matthias Hein
2018	J	`jnl`	A unifying Perron-Frobenius theorem for nonnegative tensors via multi-homogeneous maps. CoRR Antoine Gautier, Francesco Tudisco, Matthias Hein
2018	J	`jnl`	Analysis and Optimization of Loss Functions for Multiclass, Top-k, and Multilabel Classification. IEEE Trans. Pattern Anal. Mach. Intell. Maksim Lapin, Matthias Hein, Bernt Schiele
2018	J	`jnl`	Community Detection in Networks via Nonlinear Modularity Eigenvectors. SIAM J. Appl. Math. Francesco Tudisco, Pedro Mercado, Matthias Hein
2018	J	`jnl`	Disentangling Adversarial Robustness and Generalization. CoRR David Stutz, Matthias Hein, Bernt Schiele
2018	J	`jnl`	Logit Pairing Methods Can Fool Gradient-Based Attacks. CoRR Marius Mosbach, Maksym Andriushchenko, Thomas Alexander Trost, Matthias Hein, Dietrich Klakow
2018	A*	`conf`	Neural Networks Should Be Wide Enough to Learn Disconnected Decision Regions. ICML Quynh Nguyen, Mahesh Chandra Mukkamala, Matthias Hein
2018	J	`jnl`	Neural Networks Should Be Wide Enough to Learn Disconnected Decision Regions. CoRR Quynh Nguyen, Mahesh Chandra Mukkamala, Matthias Hein
2018	J	`jnl`	On the loss landscape of a class of deep neural networks with no bad local valleys. CoRR Quynh Nguyen, Mahesh Chandra Mukkamala, Matthias Hein
2018	A*	`conf`	Optimization Landscape and Expressivity of Deep CNNs. ICML Quynh Nguyen, Matthias Hein
2018	J	`jnl`	Provable Robustness of ReLU networks via Maximization of Linear Regions. CoRR Francesco Croce, Maksym Andriushchenko, Matthias Hein
2018	A	`conf`	The Power Mean Laplacian for Multilayer Graph Clustering. AISTATS Pedro Mercado, Antoine Gautier, Francesco Tudisco, Matthias Hein
2018	J	`jnl`	The Power Mean Laplacian for Multilayer Graph Clustering. CoRR Pedro Mercado, Antoine Gautier, Francesco Tudisco, Matthias Hein
2018	—	`conf`	The loss surface and expressivity of deep convolutional neural networks. ICLR (Workshop) Quynh Nguyen, Matthias Hein
2018	J	`jnl`	Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problem. CoRR Matthias Hein, Maksym Andriushchenko, Julian Bitterwolf
2017	J	`jnl`	An Efficient Multilinear Optimization Framework for Hypergraph Matching. IEEE Trans. Pattern Anal. Mach. Intell. Quynh Nguyen, Francesco Tudisco, Antoine Gautier, Matthias Hein
2017	J	`jnl`	Clustering Signed Networks with the Geometric Mean of Laplacians. CoRR Pedro Mercado, Francesco Tudisco, Matthias Hein
2017	J	`jnl`	Community detection in networks via nonlinear modularity eigenvectors. CoRR Francesco Tudisco, Pedro Mercado, Matthias Hein
2017	—	`conf`	Formal Guarantees on the Robustness of a Classifier against Adversarial Manipulation. NIPS Matthias Hein, Maksym Andriushchenko
2017	J	`jnl`	Formal Guarantees on the Robustness of a Classifier against Adversarial Manipulation. CoRR Matthias Hein, Maksym Andriushchenko
2017	A*	`conf`	Simple Does It: Weakly Supervised Instance and Semantic Segmentation. CVPR Anna Khoreva, Rodrigo Benenson, Jan Hendrik Hosang, Matthias Hein, Bernt Schiele
2017	A*	`conf`	The Loss Surface of Deep and Wide Neural Networks. ICML Quynh Nguyen, Matthias Hein
2017	J	`jnl`	The loss surface and expressivity of deep convolutional neural networks. CoRR Quynh Nguyen, Matthias Hein
2017	J	`jnl`	The loss surface of deep and wide neural networks. CoRR Quynh Nguyen, Matthias Hein
2017	A*	`conf`	Variants of RMSProp and Adagrad with Logarithmic Regret Bounds. ICML Mahesh Chandra Mukkamala, Matthias Hein
2017	J	`jnl`	Variants of RMSProp and Adagrad with Logarithmic Regret Bounds. CoRR Mahesh Chandra Mukkamala, Matthias Hein
2016	J	`jnl`	Analysis and Optimization of Loss Functions for Multiclass, Top-k, and Multilabel Classification. CoRR Maksim Lapin, Matthias Hein, Bernt Schiele
2016	—	`conf`	Clustering Signed Networks with the Geometric Mean of Laplacians. NIPS Pedro Mercado, Francesco Tudisco, Matthias Hein
2016	—	`conf`	Globally Optimal Training of Generalized Polynomial Neural Networks with Nonlinear Spectral Methods. NIPS Antoine Gautier, Quynh Nguyen, Matthias Hein
2016	J	`jnl`	Globally Optimal Training of Generalized Polynomial Neural Networks with Nonlinear Spectral Methods. CoRR Antoine Gautier, Quynh Nguyen, Matthias Hein
2016	—	`conf`	Improved Image Boundaries for Better Video Segmentation. ECCV Workshops (3) Anna Khoreva, Rodrigo Benenson, Fabio Galasso, Matthias Hein, Bernt Schiele
2016	J	`jnl`	Improved Image Boundaries for Better Video Segmentation. CoRR Anna Khoreva, Rodrigo Benenson, Fabio Galasso, Matthias Hein, Bernt Schiele
2016	A*	`conf`	Latent Embeddings for Zero-Shot Classification. CVPR Yongqin Xian, Zeynep Akata, Gaurav Sharma, Quynh Nguyen, Matthias Hein, Bernt Schiele
2016	J	`jnl`	Latent Embeddings for Zero-shot Classification. CoRR Yongqin Xian, Zeynep Akata, Gaurav Sharma, Quynh Nguyen, Matthias Hein, Bernt Schiele
2016	A*	`conf`	Loss Functions for Top-k Error: Analysis and Insights. CVPR Maksim Lapin, Matthias Hein, Bernt Schiele
2016	J	`jnl`	Nodal domain theorem for the graph p-Laplacian. CoRR Francesco Tudisco, Matthias Hein
2016	A*	`conf`	Weakly Supervised Object Boundaries. CVPR Anna Khoreva, Rodrigo Benenson, Mohamed Omran, Matthias Hein, Bernt Schiele
2016	J	`jnl`	Weakly Supervised Semantic Labelling and Instance Segmentation. CoRR Anna Khoreva, Rodrigo Benenson, Jan Hendrik Hosang, Matthias Hein, Bernt Schiele
2015	J	`jnl`	A Flexible Tensor Block Coordinate Ascent Scheme for Hypergraph Matching. CoRR Quynh Nguyen Ngoc, Antoine Gautier, Matthias Hein
2015	A*	`conf`	A flexible tensor block coordinate ascent scheme for hypergraph matching. CVPR Quynh Nguyen Ngoc, Antoine Gautier, Matthias Hein
2015	J	`jnl`	An Efficient Multilinear Optimization Framework for Hypergraph Matching. CoRR Quynh Nguyen, Francesco Tudisco, Antoine Gautier, Matthias Hein
2015	A*	`conf`	Classifier based graph construction for video segmentation. CVPR Anna Khoreva, Fabio Galasso, Matthias Hein, Bernt Schiele
2015	J	`jnl`	Constrained 1-Spectral Clustering. CoRR Syama Sundar Rangapuram, Matthias Hein
2015	J	`jnl`	Correction of noisy labels via mutual consistency check. Neurocomputing Sahely Bhadra, Matthias Hein
2015	—	`conf`	Efficient Output Kernel Learning for Multiple Tasks. NIPS Pratik Jawanpuria, Maksim Lapin, Matthias Hein, Bernt Schiele
2015	J	`jnl`	Efficient Output Kernel Learning for Multiple Tasks. CoRR Pratik Jawanpuria, Maksim Lapin, Matthias Hein, Bernt Schiele
2015	J	`jnl`	Loss Functions for Top-k Error: Analysis and Insights. CoRR Maksim Lapin, Matthias Hein, Bernt Schiele
2015	J	`jnl`	Mathematical and Computational Foundations of Learning Theory (Dagstuhl Seminar 15361). Dagstuhl Reports Matthias Hein, Gábor Lugosi, Lorenzo Rosasco
2015	—	`conf`	Regularization-Free Estimation in Trace Regression with Symmetric Positive Semidefinite Matrices. NIPS Martin Slawski, Ping Li, Matthias Hein
2015	J	`jnl`	Regularization-free estimation in trace regression with symmetric positive semidefinite matrices. CoRR Martin Slawski, Ping Li, Matthias Hein
2015	J	`jnl`	Robust PCA: Optimization of the Robust Reconstruction Error over the Stiefel Manifold. CoRR Anastasia Podosinnikova, Simon Setzer, Matthias Hein
2015	J	`jnl`	Tight Continuous Relaxation of the Balanced k-Cut Problem. CoRR Syama Sundar Rangapuram, Pramod Kaushik Mudrakarta, Matthias Hein
2015	—	`conf`	Top-k Multiclass SVM. NIPS Maksim Lapin, Matthias Hein, Bernt Schiele
2015	J	`jnl`	Top-k Multiclass SVM. CoRR Maksim Lapin, Matthias Hein, Bernt Schiele
2015	J	`jnl`	Towards Realistic Team Formation in Social Networks based on Densest Subgraphs. CoRR Syama Sundar Rangapuram, Thomas Bühler, Matthias Hein
2015	J	`jnl`	Weakly Supervised Object Boundaries. CoRR Anna Khoreva, Rodrigo Benenson, Mohamed Omran, Matthias Hein, Bernt Schiele
2014	J	`jnl`	Hitting and commute times in large random neighborhood graphs. J. Mach. Learn. Res. Ulrike von Luxburg, Agnes Radl, Matthias Hein
2014	—	`conf`	Learning Must-Link Constraints for Video Segmentation Based on Spectral Clustering. GCPR Anna Khoreva, Fabio Galasso, Matthias Hein, Bernt Schiele
2014	J	`jnl`	Learning using privileged information: SV M+ and weighted SVM. Neural Networks Maksim Lapin, Matthias Hein, Bernt Schiele
2014	J	`jnl`	Matrix factorization with Binary Components. CoRR Martin Slawski, Matthias Hein, Pavlo Lutsik
2014	—	`conf`	Robust PCA: Optimization of the Robust Reconstruction Error Over the Stiefel Manifold. GCPR Anastasia Podosinnikova, Simon Setzer, Matthias Hein
2014	A*	`conf`	Scalable Multitask Representation Learning for Scene Classification. CVPR Maksim Lapin, Bernt Schiele, Matthias Hein
2014	—	`conf`	Tight Continuous Relaxation of the Balanced k-Cut Problem. NIPS Syama Sundar Rangapuram, Pramod Kaushik Mudrakarta, Matthias Hein
2013	—	`conf`	Constrained fractional set programs and their application in local clustering and community detection. ICML (1) Thomas Bühler, Syama Sundar Rangapuram, Simon Setzer, Matthias Hein
2013	J	`jnl`	Constrained fractional set programs and their application in local clustering and community detection. CoRR Thomas Bühler, Syama Sundar Rangapuram, Simon Setzer, Matthias Hein
2013	J	`jnl`	Learning Using Privileged Information: SVM+ and Weighted SVM. CoRR Maksim Lapin, Matthias Hein, Bernt Schiele
2013	—	`conf`	Matrix factorization with binary components. NIPS Martin Slawski, Matthias Hein, Pavlo Lutsik
2013	J	`jnl`	Nonlinear Eigenproblems in Data Analysis - Balanced Graph Cuts and the RatioDCA-Prox. CoRR Leonardo Jost, Simon Setzer, Matthias Hein
2013	—	`ed.`	Pattern Recognition - 35th German Conference, GCPR 2013, Saarbrücken, Germany, September 3-6, 2013. Proceedings GCPR Joachim Weickert, Matthias Hein, Bernt Schiele
2013	—	`conf`	The Total Variation on Hypergraphs - Learning on Hypergraphs Revisited. NIPS Matthias Hein, Simon Setzer, Leonardo Jost, Syama Sundar Rangapuram
2013	J	`jnl`	The Total Variation on Hypergraphs - Learning on Hypergraphs Revisited. CoRR Matthias Hein, Simon Setzer, Leonardo Jost, Syama Sundar Rangapuram
2013	A*	`conf`	Towards realistic team formation in social networks based on densest subgraphs. WWW Syama Sundar Rangapuram, Thomas Bühler, Matthias Hein
2012	A	`conf`	Constrained 1-Spectral Clustering. AISTATS Syama Sundar Rangapuram, Matthias Hein
2012	J	`jnl`	Isotope pattern deconvolution for peptide mass spectrometry by non-negative least squares/least absolute deviation template matching. BMC Bioinform. Martin Slawski, Rene Hussong, Andreas Tholey, Thomas Jakoby, Barbara Gregorius, Andreas Hildebrandt, Matthias Hein
2011	—	`conf`	Beyond Spectral Clustering - Tight Relaxations of Balanced Graph Cuts. NIPS Matthias Hein, Simon Setzer
2011	J	`jnl`	How the result of graph clustering methods depends on the construction of the graph CoRR Markus Maier, Ulrike von Luxburg, Matthias Hein
2011	J	`jnl`	Mathematical and Computational Foundations of Learning Theory (Dagstuhl Seminar 11291). Dagstuhl Reports Matthias Hein, Gábor Lugosi, Lorenzo Rosasco, Steve Smale
2011	—	`conf`	Sparse recovery by thresholded non-negative least squares. NIPS Martin Slawski, Matthias Hein
2010	J	`jnl`	An Inverse Power Method for Nonlinear Eigenproblems with Applications in 1-Spectral Clustering and Sparse PCA CoRR Matthias Hein, Thomas Bühler
2010	—	`conf`	An Inverse Power Method for Nonlinear Eigenproblems with Applications in 1-Spectral Clustering and Sparse PCA. NIPS Matthias Hein, Thomas Bühler
2010	—	`conf`	Getting lost in space: Large sample analysis of the resistance distance. NIPS Ulrike von Luxburg, Agnes Radl, Matthias Hein
2010	J	`jnl`	Hitting times, commute distances and the spectral gap for large random geometric graphs CoRR Ulrike von Luxburg, Agnes Radl, Matthias Hein
2010	J	`jnl`	Nonparametric Regression between General Riemannian Manifolds. SIAM J. Imaging Sci. Florian Steinke, Matthias Hein, Bernhard Schölkopf
2009	J	`jnl`	Large-scale antibody profiling of human blood sera: The future of molecular diagnosis. Inform. Spektrum 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
2009	J	`jnl`	Optimal construction of k-nearest-neighbor graphs for identifying noisy clusters. Theor. Comput. Sci. Markus Maier, Matthias Hein, Ulrike von Luxburg
2009	—	`conf`	Robust Nonparametric Regression with Metric-Space Valued Output. NIPS Matthias Hein
2009	—	`conf`	Semi-supervised Regression using Hessian energy with an application to semi-supervised dimensionality reduction. NIPS Kwang In Kim, Florian Steinke, Matthias Hein
2009	A*	`conf`	Spectral clustering based on the graph ICML Thomas Bühler, Matthias Hein
2008	J	`jnl`	Enhancement of Bright Video Features for HDR Displays. Comput. Graph. Forum Piotr Didyk, Rafal Mantiuk, Matthias Hein, Hans-Peter Seidel
2008	—	`conf`	Influence of graph construction on graph-based clustering measures. NIPS Markus Maier, Ulrike von Luxburg, Matthias Hein
2008	J	`jnl`	Manifold-valued Thin-Plate Splines with Applications in Computer Graphics. Comput. Graph. Forum Florian Steinke, Matthias Hein, Jan Peters, Bernhard Schölkopf
2008	—	`conf`	Non-parametric Regression Between Manifolds. NIPS Florian Steinke, Matthias Hein
2007	B	`conf`	Cluster Identification in Nearest-Neighbor Graphs. ALT Markus Maier, Matthias Hein, Ulrike von Luxburg
2007	J	`jnl`	Graph Laplacians and their Convergence on Random Neighborhood Graphs. J. Mach. Learn. Res. Matthias Hein, Jean-Yves Audibert, Ulrike von Luxburg
2007	A*	`conf`	Manifold Denoising as Preprocessing for Finding Natural Representations of Data. AAAI Matthias Hein, Markus Maier
2006	J	`jnl`	Graph Laplacians and their convergence on random neighborhood graphs CoRR Matthias Hein, Jean-Yves Audibert, Ulrike von Luxburg
2006	—	`conf`	Manifold Denoising. NIPS Matthias Hein, Markus Maier
2006	A*	`conf`	Uniform Convergence of Adaptive Graph-Based Regularization. COLT Matthias Hein
2005	A*	`conf`	From Graphs to Manifolds - Weak and Strong Pointwise Consistency of Graph Laplacians. COLT Matthias Hein, Jean-Yves Audibert, Ulrike von Luxburg
2005	—	`—`	Geometrical aspects of statistical learning theory. Matthias Hein
2005	A	`conf`	Hilbertian Metrics and Positive Definite Kernels on Probability Measures. AISTATS Matthias Hein, Olivier Bousquet
2005	A*	`conf`	Intrinsic dimensionality estimation of submanifolds in R ICML Matthias Hein, Jean-Yves Audibert
2005	J	`jnl`	Maximal margin classification for metric spaces. J. Comput. Syst. Sci. Matthias Hein, Olivier Bousquet, Bernhard Schölkopf
2004	—	`conf`	Hilbertian Metrics on Probability Measures and Their Application in SVM?s. DAGM-Symposium Matthias Hein, Thomas Navin Lal, Olivier Bousquet
2003	A*	`conf`	Maximal Margin Classification for Metric Spaces. COLT Matthias Hein, Olivier Bousquet
2003	—	`conf`	Measure Based Regularization. NIPS Olivier Bousquet, Olivier Chapelle, Matthias Hein