12 citations · 38 across the 7 of their papers we have counts for
8 papers
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…
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…
Multi-dimensional concept discovery (MCD): A unifying framework with completeness guarantees
Johanna Vielhaben, Stefan Blücher, Nils Strodthoff
The completeness axiom renders the explanation of a post-hoc XAI method only locally faithful to the model, i.e. for a single decision. For the trustworthy application of XAI, in p…
Sparse Subspace Clustering for Concept Discovery (SSCCD)
Johanna Vielhaben, Stefan Blücher, Nils Strodthoff
Concepts are key building blocks of higher level human understanding. Explainable AI (XAI) methods have shown tremendous progress in recent years, however, local attribution method…
Predicting the Binding of SARS-CoV-2 Peptides to the Major Histocompatibility Complex with Recurrent Neural Networks
Johanna Vielhaben, Markus Wenzel, Eva Weicken +1
Predicting the binding of viral peptides to the major histocompatibility complex with machine learning can potentially extend the computational immunology toolkit for vaccine devel…
PredDiff: Explanations and Interactions from Conditional Expectations
Stefan Blücher, Johanna Vielhaben, Nils Strodthoff
PredDiff is a model-agnostic, local attribution method that is firmly rooted in probability theory. Its simple intuition is to measure prediction changes while marginalizing featur…
Generative Neural Samplers for the Quantum Heisenberg Chain
Johanna Vielhaben, Nils Strodthoff
Generative neural samplers offer a complementary approach to Monte Carlo methods for problems in statistical physics and quantum field theory. This work tests the ability of genera…