7 papers
CHiQPM: Calibrated Hierarchical Interpretable Image Classification
Thomas Norrenbrock, Timo Kaiser, Sovan Biswas +3
Globally interpretable models are a promising approach for trustworthy AI in safety-critical domains. Alongside global explanations, detailed local explanations are a crucial compl…
Improved Convex Decomposition with Ensembling and Negative Primitives
Vaibhav Vavilala, Florian Kluger, Seemandhar Jain +3
Describing a scene in terms of primitives -- geometrically simple shapes that offer a parsimonious but accurate abstraction of structure -- is an established and difficult fitting…
Improving 3D Foot Motion Reconstruction in Markerless Monocular Human Motion Capture
Tom Wehrbein, Bodo Rosenhahn
State-of-the-art methods can recover accurate overall 3D human body motion from in-the-wild videos. However, they often fail to capture fine-grained articulations, especially in th…
Interpretable Decision-Making for End-to-End Autonomous Driving
Mona Mirzaie, Bodo Rosenhahn
Trustworthy AI is mandatory for the broad deployment of autonomous vehicles. Although end-to-end approaches derive control commands directly from raw data, interpreting these decis…
UncertainSAM: Fast and Efficient Uncertainty Quantification of the Segment Anything Model
Timo Kaiser, Thomas Norrenbrock, Bodo Rosenhahn
The introduction of the Segment Anything Model (SAM) has paved the way for numerous semantic segmentation applications. For several tasks, quantifying the uncertainty of SAM is of…
S4ConvD: Adaptive Scaling and Frequency Adjustment for Energy-Efficient Sensor Networks in Smart Buildings
Melanie Schaller, Bodo Rosenhahn
Predicting energy consumption in smart buildings is challenging due to dependencies in sensor data and the variability of environmental conditions. We introduce S4ConvD, a novel co…