activity
20212024
most citedDo Users Benefit From Interpretable Vision? A User Study, Baseline, And Dataset

5 citations · 11 across the 5 of their papers we have counts for

collaborators

6 papers

cs.LG2024

Causal discovery with endogenous context variables

Wiebke Günther, Oana-Iuliana Popescu, Martin Rabel +3

Causal systems often exhibit variations of the underlying causal mechanisms between the variables of the system. Often, these changes are driven by different environments or intern…

cs.AI2024★ 3 cited

AI for Extreme Event Modeling and Understanding: Methodologies and Challenges

Gustau Camps-Valls, Miguel-Ángel Fernández-Torres, Kai-Hendrik Cohrs +22

In recent years, artificial intelligence (AI) has deeply impacted various fields, including Earth system sciences. Here, AI improved weather forecasting, model emulation, parameter…

cs.LG2023

Non-parametric Conditional Independence Testing for Mixed Continuous-Categorical Variables: A Novel Method and Numerical Evaluation

Oana-Iuliana Popescu, Andreas Gerhardus, Jakob Runge

Conditional independence testing (CIT) is a common task in machine learning, e.g., for variable selection, and a main component of constraint-based causal discovery. While most cur…

cs.CL2023

Automated multilingual detection of Pro-Kremlin propaganda in newspapers and Telegram posts

Veronika Solopova, Oana-Iuliana Popescu, Christoph Benzmüller +1

The full-scale conflict between the Russian Federation and Ukraine generated an unprecedented amount of news articles and social media data reflecting opposing ideologies and narra…

cs.LG2022★ 5 cited

Do Users Benefit From Interpretable Vision? A User Study, Baseline, And Dataset

Leon Sixt, Martin Schuessler, Oana-Iuliana Popescu +2

A variety of methods exist to explain image classification models. However, whether they provide any benefit to users over simply comparing various inputs and the model's respectiv…

cs.CV2021★ 3 cited

Counterfactual Generation with Knockoffs

Oana-Iuliana Popescu, Maha Shadaydeh, Joachim Denzler

Human interpretability of deep neural networks' decisions is crucial, especially in domains where these directly affect human lives. Counterfactual explanations of already trained…