activity
20182025
most citedMulti-dimensional concept discovery (MCD): A unifying framework with completeness guarantees

12 citations · 28 across the 8 of their papers we have counts for

collaborators

12 papers

cs.CV2025

FeatInv: Spatially resolved mapping from feature space to input space using conditional diffusion models

Nils Neukirch, Johanna Vielhaben, Nils Strodthoff

Internal representations are crucial for understanding deep neural networks, such as their properties and reasoning patterns, but remain difficult to interpret. While mapping from…

cs.LG2025★ 2 cited

Mechanistic understanding and validation of large AI models with SemanticLens

Maximilian Dreyer, Jim Berend, Tobias Labarta +4

Unlike human-engineered systems such as aeroplanes, where each component's role and dependencies are well understood, the inner workings of AI models remain largely opaque, hinderi…

cs.CV2024

Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformers

Johanna Vielhaben, Dilyara Bareeva, Jim Berend +2

Vision transformers (ViTs) can be trained using various learning paradigms, from fully supervised to self-supervised. Diverse training protocols often result in significantly diffe…

cs.CV2024★ 2 cited

PURE: Turning Polysemantic Neurons Into Pure Features by Identifying Relevant Circuits

Maximilian Dreyer, Erblina Purelku, Johanna Vielhaben +2

The field of mechanistic interpretability aims to study the role of individual neurons in Deep Neural Networks. Single neurons, however, have the capability to act polysemantically…

cs.CV2024★ 6 cited

Decoupling Pixel Flipping and Occlusion Strategy for Consistent XAI Benchmarks

Stefan Blücher, Johanna Vielhaben, Nils Strodthoff

Feature removal is a central building block for eXplainable AI (XAI), both for occlusion-based explanations (Shapley values) as well as their evaluation (pixel flipping, PF). Howev…

cs.SD2023★ 4 cited

XAI-based Comparison of Input Representations for Audio Event Classification

Annika Frommholz, Fabian Seipel, Sebastian Lapuschkin +2

Deep neural networks are a promising tool for Audio Event Classification. In contrast to other data like natural images, there are many sensible and non-obvious representations for…