Showing cs.LGShow all
2 papers · 1 filter
cs.LG2024
Learning with Confidence: Training Better Classifiers from Soft Labels
Sjoerd de Vries, Dirk Thierens
In supervised machine learning, models are typically trained using data with hard labels, i.e., definite assignments of class membership. This traditional approach, however, does n…
cs.LG2024
Generating the Ground Truth: Synthetic Data for Soft Label and Label Noise Research
Sjoerd de Vries, Dirk Thierens
In many real-world classification tasks, label noise is an unavoidable issue that adversely affects the generalization error of machine learning models. Additionally, evaluating ho…