Matthias Hein

6

Papers

23

Total Citations

Papers (6)

Towards Reliable Evaluation and Fast Training of Robust Semantic Segmentation Models

DiG-IN: Diffusion Guidance for Investigating Networks - Uncovering Classifier Differences Neuron Visualisations and Visual Counterfactual Explanations

Advancing Compositional Awareness in CLIP with Efficient Fine-Tuning

DASH: Detection and Assessment of Systematic Hallucinations of VLMs

Bias of Stochastic Gradient Descent or the Architecture: Disentangling the Effects of Overparameterization of Neural Networks

Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models