Search Results for author:
Found 2 papers, 0 papers with code
Unaligned but Safe -- Formally Compensating Performance Limitations for Imprecise 2D Object Detection
We address a special sub-type of performance limitations: the prediction bounding box cannot be perfectly aligned with the ground truth, but the computed Intersection-over-Union metric is always larger than a given threshold.
Logically Sound Arguments for the Effectiveness of ML Safety Measures
We investigate the issues of achieving sufficient rigor in the arguments for the safety of machine learning functions.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
