← Search

Leander Weber

2 accepted papers

2025

Navigating Neural Space: Revisiting Concept Activation Vectors to Overcome Directional Divergence

ICLR 2025poster

With a growing interest in understanding neural network prediction strategies, Concept Activation Vectors (CAVs) have emerged as a popular tool for modeling human-understandable concepts in the latent space. Commonly, CAVs are computed by leveraging linear classifiers optimizing the *separability* o…

Cited by 5SourcePDFScholar
2023

Shortcomings of Top-Down Randomization-Based Sanity Checks for Evaluations of Deep Neural Network Explanations

CVPR 2023poster

While the evaluation of explanations is an important step towards trustworthy models, it needs to be done carefully, and the employed metrics need to be well-understood. Specifically model randomization testing can be overinterpreted if regarded as a primary criterion for selecting or discarding exp…

Cited by 27SourcePDFScholar