Boosting EfficientNets Ensemble Performance via Pseudo-Labels and Synthetic Images by pix2pixHD for Infection and Ischaemia Classification in Diabetic Foot Ulcers.
Louise BlochRaphael BrüngelChristoph M. FriedrichPublished in: DFUC@MICCAI (2021)
Keyphrases
- ensemble classification
- class labels
- weak learners
- training set
- ensemble classifier
- ensemble methods
- ensemble learning
- base classifiers
- classification accuracy
- feature selection
- multiple classifier systems
- weak classifiers
- decision trees
- accurate classifiers
- final classification
- learning algorithm
- combining classifiers
- machine learning methods
- classification algorithm
- model selection
- machine learning
- feature vectors
- training data
- classification trees
- regression problems
- majority voting
- support vector machine svm
- text classification
- multiple classifiers
- active learning
- support vector
- binary classification problems
- feature extraction
- multiclass classification
- partially labeled data
- confidence scores
- randomized trees
- random forests
- cost sensitive
- cross validation
- benchmark datasets
- machine learning algorithms
- training examples
- supervised learning
- classifier ensemble
- multi label classification
- risk factors
- classifier combination
- classification models
- multi label
- diabetes mellitus
- image classification