118 citations · 141 across the 5 of their papers we have counts for
4 papers · 1 filter
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…
Quanda: An Interpretability Toolkit for Training Data Attribution Evaluation and Beyond
Dilyara Bareeva, Galip Ümit Yolcu, Anna Hedström +4
In recent years, training data attribution (TDA) methods have emerged as a promising direction for the interpretability of neural networks. While research around TDA is thriving, l…
Reactive Model Correction: Mitigating Harm to Task-Relevant Features via Conditional Bias Suppression
Dilyara Bareeva, Maximilian Dreyer, Frederik Pahde +2
Deep Neural Networks are prone to learning and relying on spurious correlations in the training data, which, for high-risk applications, can have fatal consequences. Various approa…
Manipulating Feature Visualizations with Gradient Slingshots
Dilyara Bareeva, Marina M. -C. Höhne, Alexander Warnecke +5
Feature Visualization (FV) is a widely used technique for interpreting concepts learned by Deep Neural Networks (DNNs), which synthesizes input patterns that maximally activate a g…