12 citations · 42 across the 10 of their papers we have counts for
4 papers · 1 filter
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…
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…
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…
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…