110 citations · 186 across the 9 of their papers we have counts for
10 papers
The Gaussian Discriminant Variational Autoencoder (GdVAE): A Self-Explainable Model with Counterfactual Explanations
Anselm Haselhoff, Kevin Trelenberg, Fabian Küppers +1
Visual counterfactual explanation (CF) methods modify image concepts, e.g, shape, to change a prediction to a predefined outcome while closely resembling the original query image.…
Quantifying Local Model Validity using Active Learning
Sven Lämmle, Can Bogoclu, Robert Voßhall +2
Real-world applications of machine learning models are often subject to legal or policy-based regulations. Some of these regulations require ensuring the validity of the model, i.e…
Segmentation-guided Domain Adaptation for Efficient Depth Completion
Fabian Märkert, Martin Sunkel, Anselm Haselhoff +1
Complete depth information and efficient estimators have become vital ingredients in scene understanding for automated driving tasks. A major problem for LiDAR-based depth completi…
Parametric and Multivariate Uncertainty Calibration for Regression and Object Detection
Fabian Küppers, Jonas Schneider, Anselm Haselhoff
Reliable spatial uncertainty evaluation of object detection models is of special interest and has been subject of recent work. In this work, we review the existing definitions for…
Confidence Calibration for Object Detection and Segmentation
Fabian Küppers, Anselm Haselhoff, Jan Kronenberger +1
Calibrated confidence estimates obtained from neural networks are crucial, particularly for safety-critical applications such as autonomous driving or medical image diagnosis. Howe…
Bayesian Confidence Calibration for Epistemic Uncertainty Modelling
Fabian Küppers, Jan Kronenberger, Jonas Schneider +1
Modern neural networks have found to be miscalibrated in terms of confidence calibration, i.e., their predicted confidence scores do not reflect the observed accuracy or precision.…
Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety
Sebastian Houben, Stephanie Abrecht, Maram Akila +38
The use of deep neural networks (DNNs) in safety-critical applications like mobile health and autonomous driving is challenging due to numerous model-inherent shortcomings. These s…
From Black-box to White-box: Examining Confidence Calibration under different Conditions
Franziska Schwaiger, Maximilian Henne, Fabian Küppers +3
Confidence calibration is a major concern when applying artificial neural networks in safety-critical applications. Since most research in this area has focused on classification i…
Dependency Decomposition and a Reject Option for Explainable Models
Jan Kronenberger, Anselm Haselhoff
Deploying machine learning models in safety-related do-mains (e.g. autonomous driving, medical diagnosis) demands for approaches that are explainable, robust against adversarial at…
Multivariate Confidence Calibration for Object Detection
Fabian Küppers, Jan Kronenberger, Amirhossein Shantia +1
Unbiased confidence estimates of neural networks are crucial especially for safety-critical applications. Many methods have been developed to calibrate biased confidence estimates.…