Showing cs.LGShow all
3 papers · 1 filter
cs.LG2025
Generative Example-Based Explanations: Bridging the Gap between Generative Modeling and Explainability
Philipp Vaeth, Alexander M. Fruehwald, Benjamin Paassen +1
Recently, several methods have leveraged deep generative modeling to produce example-based explanations of image classifiers. Despite producing visually stunning results, these met…
cs.LG2025
Diffusion Classifier Guidance for Non-robust Classifiers
Philipp Vaeth, Dibyanshu Kumar, Benjamin Paassen +1
Classifier guidance is intended to steer a diffusion process such that a given classifier reliably recognizes the generated data point as a certain class. However, most classifier…
cs.LG2024
GradCheck: Analyzing classifier guidance gradients for conditional diffusion sampling
Philipp Vaeth, Alexander M. Fruehwald, Benjamin Paassen +1
To sample from an unconditionally trained Denoising Diffusion Probabilistic Model (DDPM), classifier guidance adds conditional information during sampling, but the gradients from c…