Industrial defect detection on the edge with deep learning over scarcely labeled and extremely imbalanced data.
Joe LorentzThomas HartmannAssaad MoawadDjamila AouadaPublished in: COINS (2023)
Keyphrases
- deep learning
- defect detection
- imbalanced data
- unsupervised learning
- linear regression
- class distribution
- supervised learning
- feature selection
- support vector machine
- machine learning
- training data
- ensemble methods
- feature extraction
- classification models
- sampling methods
- class imbalance
- mental models
- decision trees
- random forest
- weakly supervised
- pairwise
- pattern recognition
- data mining
- image classification