2 papers
cs.LG2024
Towards Reducing Data Acquisition and Labeling for Defect Detection using Simulated Data
Lukas Malte Kemeter, Rasmus Hvingelby, Paulina Sierak +2
In many manufacturing settings, annotating data for machine learning and computer vision is costly, but synthetic data can be generated at significantly lower cost. Substituting th…
cs.LG2024
Position: Embracing Negative Results in Machine Learning
Florian Karl, Lukas Malte Kemeter, Gabriel Dax +1
Publications proposing novel machine learning methods are often primarily rated by exhibited predictive performance on selected problems. In this position paper we argue that predi…