3 papers
cs.CV2026
On the Faithfulness of Post-Hoc Concept Bottleneck Models
Laines Schmalwasser, Jan Blunk, Niklas Penzel +2
Human decision-making interprets the world through high-level concepts, such as recognizing a bird by its belly color. To bridge the gap between opaque deep learning representation…
cs.LG2025
FastCAV: Efficient Computation of Concept Activation Vectors for Explaining Deep Neural Networks
Laines Schmalwasser, Niklas Penzel, Joachim Denzler +1
Concepts such as objects, patterns, and shapes are how humans understand the world. Building on this intuition, concept-based explainability methods aim to study representations le…
cs.CV2024
Exploiting Text-Image Latent Spaces for the Description of Visual Concepts
Laines Schmalwasser, Jakob Gawlikowski, Joachim Denzler +1
Concept Activation Vectors (CAVs) offer insights into neural network decision-making by linking human friendly concepts to the model's internal feature extraction process. However,…