MH
Matthias Hein
cs.LGcs.CVstat.MLcs.CRcs.AImath.OCcs.NAmath.NAcond-mat.supr-concs.DS
On Valency
published · living versionsW_dfxx4kxk·v1 · currentpublished
Bit Error Robustness for Energy-Efficient DNN Accelerators
with David Stutz, Nandhini Chandramoorthy, Bernt Schiele
1 version
Preprints & journals
129 papers in the corpus · 1995–2025Collapse of the superconducting order parameter in Ising superconductors with Rashba spin-orbit coupling2512.01910v2 · J. S. Harms, M. Hein, W. Belzig2025 · 0 citationsarXiv
Definition and Validation of an Exposure Measurement Method for a Typical Load of a Base Station.41175046 · Schiffarth, Anna-Malin, Ta, Tam Julian, Bornkessel, Christian et al.2025 · 4 citationsBioelectromagnetics. 2025;46(8):e70029
Influence of Transmission Rank on EMF Exposure Measured With Provoked Data Traffic Around 5G Massive MIMO Base Stations2511.17212v1 · Lisa-Marie Schilling, Christian Bornkessel, Anna-Malin Schiffarth et al.2025 · 0 citationsarXiv
A Definition of AGI2510.18212v3 · Dan Hendrycks, Dawn Song, Christian Szegedy et al.2025 · 3 citationsarXiv
Wideband Antenna Deconvolution for Bistatic Millimeter Wave Radar Reflectivity Measurements2510.16094v2 · Carsten Andrich, Isabella Varga, Tobias F. Nowack et al.2025 · 0 citations2026 20th European Conference on Antennas and Propagation (EuCAP)
Unlearning That Lasts: Utility-Preserving, Robust, and Almost Irreversible Forgetting in LLMs2509.02820v1 · Naman Deep Singh, Maximilian Muller, Francesco Croce et al.2025 · 0 citationsarXiv
Mind the Detail: Uncovering Clinically Relevant Image Details in Accelerated MRI with Semantically Diverse Reconstructions2507.00670v1 · Jan Nikolas Morshuis, Christian Schlarmann, Thomas Kustner et al.2025 · 0 citationsarXiv
FuseLIP: Multimodal Embeddings via Early Fusion of Discrete Tokens2506.03096v2 · Christian Schlarmann, Francesco Croce, Nicolas Flammarion et al.2025 · 0 citationsarXiv
Robustness in Both Domains: CLIP Needs a Robust Text Encoder2506.03355v2 · Elias Abad Rocamora, Christian Schlarmann, Naman Deep Singh et al.2025 · 0 citationsarXiv
Improving Knowledge Distillation Under Unknown Covariate Shift Through Confidence-Guided Data Augmentation2506.02294v4 · Niclas Popp, Kevin Alexander Laube, Matthias Hein et al.2025 · 0 citationsarXiv
Advancing Compositional Awareness in CLIP with Efficient Fine-Tuning2505.24424v2 · Amit Peleg, Naman Deep Singh, Matthias Hein2025 · 2 citationsarXiv
Development and validation of an AI algorithm to generate realistic and meaningful counterfactuals for retinal imaging based on diffusion models.40373008 · Ilanchezian, Indu, Boreiko, Valentyn, Kühlewein, Laura et al.2026 · 8 citationsPLOS digital health. 2025;4(5):e0000853
RePOPE: Impact of Annotation Errors on the POPE Benchmark2504.15707v1 · Yannic Neuhaus, Matthias Hein2025 · 0 citationsarXiv
Adversarially Robust CLIP Models Can Induce Better (Robust) Perceptual Metrics2502.11725v1 · Francesco Croce, Christian Schlarmann, Naman Deep Singh et al.2025 · 1 citationarXiv
Single-Pass Object-Focused Data Selection2412.10032v2 · Niclas Popp, Dan Zhang, Jan Hendrik Metzen et al.2024 · 0 citationsarXiv
Perturb and Recover: Fine-tuning for Effective Backdoor Removal from CLIP2412.00727v3 · Naman Deep Singh, Francesco Croce, Matthias Hein2024 · 0 citationsarXiv
An Interpretable N-gram Perplexity Threat Model for Large Language Model Jailbreaks2410.16222v2 · Valentyn Boreiko, Alexander Panfilov, Vaclav Voracek et al.2024 · 0 citationsarXiv
LoGex: Improved tail detection of extremely rare histopathology classes via guided diffusion2409.01317v1 · Maximilian Mueller, Matthias Hein2024 · 0 citationsarXiv
Segmentation-guided MRI reconstruction for meaningfully diverse reconstructions2407.18026v1 · Jan Nikolas Morshuis, Matthias Hein, Christian F. Baumgartner2024 · 3 citationsarXiv
BIRA: A Spherical Bistatic Radar Reflectivity Measurement System2407.13749v5 · Carsten Andrich, Tobias F. Nowack, Alexander Ihlow et al.2024 · 4 citationsIEEE Transactions on Antennas and Propagation (Early Access), 2026
Bias of Stochastic Gradient Descent or the Architecture: Disentangling the Effects of Overparameterization of Neural Networks2407.03848v2 · Amit Peleg, Matthias Hein2024 · 0 citationsarXiv
How to train your ViT for OOD Detection2405.17447v1 · Maximilian Mueller, Matthias Hein2024 · 0 citationsarXiv
Zero-Shot Distillation for Image Encoders: How to Make Effective Use of Synthetic Data2404.16637v1 · Niclas Popp, Jan Hendrik Metzen, Matthias Hein2024 · 0 citationsarXiv
Identification of Fine-grained Systematic Errors via Controlled Scene Generation2404.07045v1 · Valentyn Boreiko, Matthias Hein, Jan Hendrik Metzen2024 · 0 citationsarXiv
Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models2402.12336v2 · Christian Schlarmann, Naman Deep Singh, Francesco Croce et al.2024 · 9 citationsarXiv
DiG-IN: Diffusion Guidance for Investigating Networks -- Uncovering Classifier Differences Neuron Visualisations and Visual Counterfactual Explanations2311.17833v3 · Maximilian Augustin, Yannic Neuhaus, Matthias Hein2023 · 4 citationsarXiv
Segment (Almost) Nothing: Prompt-Agnostic Adversarial Attacks on Segmentation Models2311.14450v1 · Francesco Croce, Matthias Hein2023 · 3 citationsarXiv
Generating Realistic Counterfactuals for Retinal Fundus and OCT Images using Diffusion Models2311.11629v2 · Indu Ilanchezian, Valentyn Boreiko, Laura Kuhlewein et al.2023 · 3 citationsarXiv
Identifying Systematic Errors in Object Detectors with the SCROD Pipeline2309.13489v1 · Valentyn Boreiko, Matthias Hein, Jan Hendrik Metzen2023 · 6 citationsarXiv
On the Adversarial Robustness of Multi-Modal Foundation Models2308.10741v1 · Christian Schlarmann, Matthias Hein2023 · 78 citationsarXiv
Towards Reliable Evaluation and Fast Training of Robust Semantic Segmentation Models2306.12941v2 · Francesco Croce, Naman D Singh, Matthias Hein2023 · 7 citationsarXiv
In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluation2306.00826v1 · Julian Bitterwolf, Maximilian Muller, Matthias Hein2023 · 20 citationsarXiv
Random and Adversarial Bit Error Robustness: Energy-Efficient and Secure DNN Accelerators.37815955 · Stutz, David, Chandramoorthy, Nandhini, Hein, Matthias et al.2023 · 21 citationsIEEE transactions on pattern analysis and machine intelligence. 2023;45(3):3632-3647
K2S Challenge: From Undersampled K-Space to Automatic Segmentation.36829761 · Tolpadi, Aniket A, Bharadwaj, Upasana, Gao, Kenneth T et al.2026 · 24 citationsBioengineering (Basel, Switzerland). 2023;10(2)
A Modern Look at the Relationship between Sharpness and Generalization2302.07011v2 · Maksym Andriushchenko, Francesco Croce, Maximilian Muller et al.2023 · 4 citationsarXiv
Spurious Features Everywhere -- Large-Scale Detection of Harmful Spurious Features in ImageNet2212.04871v2 · Yannic Neuhaus, Maximilian Augustin, Valentyn Boreiko et al.2022 · 19 citationsarXiv
On the interplay of adversarial robustness and architecture components: patches, convolution and attention2209.06953v1 · Francesco Croce, Matthias Hein2022 · 4 citationsarXiv
Certified Defences Against Adversarial Patch Attacks on Semantic Segmentation2209.05980v2 · Maksym Yatsura, Kaspar Sakmann, N. Grace Hua et al.2022 · 5 citationsarXiv
Adversarial Robustness of MR Image Reconstruction under Realistic Perturbations2208.03161v1 · Jan Nikolas Morshuis, Sergios Gatidis, Matthias Hein et al.2022 · 15 citationsarXiv
Provably Adversarially Robust Nearest Prototype Classifiers2207.07208v1 · V'aclav Vor'acek, Matthias Hein2022 · 4 citationsarXiv
Sound Randomized Smoothing in Floating-Point Arithmetics2207.07209v2 · V'aclav Vor'acek, Matthias Hein2022 · 1 citationarXiv
Visual explanations for the detection of diabetic retinopathy from retinal fundus images10.1101/2022.07.06.22276633v1 · Boreiko, V., Ilanchezian, I., Ayhan, M. et al.2022 · 15 citationsmedRxiv
Breaking Down Out-of-Distribution Detection: Many Methods Based on OOD Training Data Estimate a Combination of the Same Core Quantities2206.09880v1 · Julian Bitterwolf, Alexander Meinke, Maximilian Augustin et al.2022 · 5 citationsarXiv
Sparse Visual Counterfactual Explanations in Image Space2205.07972v2 · Valentyn Boreiko, Maximilian Augustin, Francesco Croce et al.2022 · 27 citationsGCPR 2022
Evaluating the Adversarial Robustness of Adaptive Test-time Defenses2202.13711v2 · Francesco Croce, Sven Gowal, Thomas Brunner et al.2022 · 17 citationsarXiv
Meta-Learning the Search Distribution of Black-Box Random Search Based Adversarial Attacks2111.01714v3 · Maksym Yatsura, Jan Hendrik Metzen, Matthias Hein2021 · 5 citationsarXiv
Being a Bit Frequentist Improves Bayesian Neural Networks2106.10065v3 · Agustinus Kristiadi, Matthias Hein, Philipp Hennig2021 · 3 citationsarXiv
Provably Robust Detection of Out-of-distribution Data (almost) for free2106.04260v2 · Alexander Meinke, Julian Bitterwolf, Matthias Hein2021 · 6 citationsarXiv
Adversarial Robustness against Multiple and Single -Threat Models via Quick Fine-Tuning of Robust Classifiers2105.12508v2 · Francesco Croce, Matthias Hein2021 · 5 citationsarXiv
Relating Adversarially Robust Generalization to Flat Minima2104.04448v2 · David Stutz, Matthias Hein, Bernt Schiele2021 · 32 citationsarXiv
Career total: 658 works. 129 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.