3 papers
cs.CV2026
Multi-Depth Concept Extraction for Post-Hoc Vision Encoder Explanation
Ahcène Boubekki, Samuel G. Fadel, Sebastian Mair
Explainable AI methods for vision models aim to identify the parts of the input that are important for the final prediction and subsequently relate these regions to human-understan…
stat.ML2025
VIKING: Deep variational inference with stochastic projections
Samuel G. Fadel, Hrittik Roy, Nicholas Krämer +5
Variational mean field approximations tend to struggle with contemporary overparametrized deep neural networks. Where a Bayesian treatment is usually associated with high-quality p…
cs.CV2024
Leveraging Activations for Superpixel Explanations
Ahcène Boubekki, Samuel G. Fadel, Sebastian Mair
Saliency methods have become standard in the explanation toolkit of deep neural networks. Recent developments specific to image classifiers have investigated region-based explanati…