Matthias Hein
- Papers
- 11
Cite
Notes
Only stored in your browser.
Authored papers
11Visual Memory Injection Attacks for Multi-Turn Conversations
arXiv 2026
Robustness in Both Domains: CLIP Needs a Robust Text Encoder
arXiv 2025
RePOPE: Impact of Annotation Errors on the POPE Benchmark
arXiv 2025
DASH: Detection and Assessment of Systematic Hallucinations of VLMs
ICCV 2025
Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models
arXiv 2024
Towards Reliable Evaluation and Fast Training of Robust Semantic Segmentation Models
arXiv 2023
A Modern Look at the Relationship between Sharpness and Generalization
arXiv 2023
Normalization Layers Are All That Sharpness-Aware Minimization Needs
normalization-layers-are-all-that-sharpness
In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluation
arXiv 2023
DiG-IN: Diffusion Guidance for Investigating Networks -- Uncovering Classifier Differences Neuron Visualisations and Visual Counterfactual Explanations
arXiv 2023
Spurious Features Everywhere -- Large-Scale Detection of Harmful Spurious Features in ImageNet
arXiv 2022
Affiliations
Frequent co-authors
10from 11 papers
Yannic Neuhaus
Christian Schlarmann
Francesco Croce
Maximilian Augustin
Maximilian Müller
Naman Deep Singh
David Rolnick
Elias Abad Rocamora
Julian Bitterwolf
Maksym Andriushchenko