Semi-Supervised Learning With Wafer-Specific Augmentations for Wafer Defect Classification
TL;DR
Semi-supervised learning improves wafer defect classification by using labeled and unlabeled data, especially when labeled data is limited. It outperforms supervised models but faces challenges with conventional image augmentations for wafer bin maps.
Semi-Supervised Learning With Wafer-Specific Augmentations for Wafer Defect Classification
Uk Jo; Seoung Bum Kim
https://doi.org/10.1109/ACCESS.2024.3522180
Volume 13
Semi-supervised learning (SSL) models, which leverage both labeled and unlabeled datasets, have been increasingly applied to classify wafer bin map patterns in semiconductor manufacturing. These models typically outperform supervised learning models in scenarios where labeled data are scarce. However, the challenges posed by wafer bin map data in applying conventional image augmentation methods, p...