262 citations · 272 across the 13 of their papers we have counts for
4 papers · 1 filter
Leveraging Color Channel Independence for Improved Unsupervised Object Detection
Bastian Jäckl, Yannick Metz, Udo Schlegel +2
Object-centric architectures can learn to extract distinct object representations from visual scenes, enabling downstream applications on the object level. Similarly to autoencoder…
Interactive dense pixel visualizations for time series and model attribution explanations
Udo Schlegel, Daniel A. Keim
The field of Explainable Artificial Intelligence (XAI) for Deep Neural Network models has developed significantly, offering numerous techniques to extract explanations from models.…
Interactive Counterfactual Generation for Univariate Time Series
Udo Schlegel, Julius Rauscher, Daniel A. Keim
We propose an interactive methodology for generating counterfactual explanations for univariate time series data in classification tasks by leveraging 2D projections and decision b…
Finding the DeepDream for Time Series: Activation Maximization for Univariate Time Series
Udo Schlegel, Daniel A. Keim, Tobias Sutter
Understanding how models process and interpret time series data remains a significant challenge in deep learning to enable applicability in safety-critical areas such as healthcare…