Zobrazeno 1 - 10
of 442
pro vyhledávání: '"A. Haselhoff"'
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. Unlike self-explainable models (SEMs) and heatmap techniques, they gra
Externí odkaz:
http://arxiv.org/abs/2409.12952
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., the approximation error being smaller than a threshold. A global me
Externí odkaz:
http://arxiv.org/abs/2406.07474
Autor:
Jedrusiak, Mikel D., Harweg, Thomas, Haselhoff, Timo, Lawrence, Bryce T., Moebus, Susanne, Weichert, Frank
Soundscapes have been studied by researchers from various disciplines, each with different perspectives, goals, approaches, and terminologies. Accordingly, depending on the field, the concept of a soundscape's components changes, consequently changin
Externí odkaz:
http://arxiv.org/abs/2310.13404
Complete depth information and efficient estimators have become vital ingredients in scene understanding for automated driving tasks. A major problem for LiDAR-based depth completion is the inefficient utilization of convolutions due to the lack of c
Externí odkaz:
http://arxiv.org/abs/2210.09213
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 uncertainty calibration of probabilistic regression tasks. We inspect
Externí odkaz:
http://arxiv.org/abs/2207.01242
Publikováno v:
Ecological Indicators, Vol 166, Iss , Pp 112547- (2024)
The association of urban greenspace and human health and well-being is widely recognised, but the underlying mechanisms are incompletely understood. The acoustic environment (AE) is frequently proposed as a mediator between greenspace and human healt
Externí odkaz:
https://doaj.org/article/8e6ca4008fda4d5d9df24ff78a3b3c01
Publikováno v:
In: Tim Fingerscheidt, Hanno Gottschalk, Sebastian Houben (eds.): "Deep Neural Networks and Data for Automated Driving", pp. 225--250, Springer Nature, Switzerland, 2022
Calibrated confidence estimates obtained from neural networks are crucial, particularly for safety-critical applications such as autonomous driving or medical image diagnosis. However, although the task of confidence calibration has been investigated
Externí odkaz:
http://arxiv.org/abs/2202.12785
Publikováno v:
In Ecological Indicators September 2024 166
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. Recent work has introduced methods for post-hoc confidence calibratio
Externí odkaz:
http://arxiv.org/abs/2109.10092
Autor:
Schmiege, Dennis, Haselhoff, Timo, Thomas, Alexander, Kraiselburd, Ivana, Meyer, Folker, Moebus, Susanne
Publikováno v:
In International Journal of Hygiene and Environmental Health June 2024 259