[HTML][HTML] Corner cases in machine learning processes
F Heidecker, M Bieshaar, B Sick - AI Perspectives & Advances, 2024 - Springer
Applications using machine learning (ML), such as highly autonomous driving, depend
highly on the performance of the ML model. The data amount and quality used for model …
highly on the performance of the ML model. The data amount and quality used for model …
Criteria for Uncertainty-based Corner Cases Detection in Instance Segmentation
F Heidecker, A El-Khateeb, M Bieshaar… - arXiv preprint arXiv …, 2024 - arxiv.org
The operating environment of a highly automated vehicle is subject to change, eg, weather,
illumination, or the scenario containing different objects and other participants in which the …
illumination, or the scenario containing different objects and other participants in which the …
[PDF][PDF] Relevance Estimation of Corner Cases for Semantic Segmentation Jasmin Breitenstein, Tim Fingscheidt| TU BS Maria Lyssenko, Maarten Bieshaar| Bosch …
F Heidecker, B Sick, U Kassel - ki-datatooling.de
Conclusions: The novel relevance-adapted mIoU is adapted to the task of corner case
identification. It establishes a link between knowledge-driven corner case types and …
identification. It establishes a link between knowledge-driven corner case types and …