Skin lesion classification with ensemble of squeeze-and-excitation networks and semi-supervised learning.
Shunsuke KitadaHitoshi IyatomiPublished in: CoRR (2018)
Keyphrases
- semi supervised learning
- supervised learning
- improve the classification accuracy
- semi supervised classification
- semi supervised
- co training
- skin lesion
- unlabeled data
- training data
- machine learning
- labeled data
- semi supervised learning algorithms
- unsupervised learning
- transductive support vector machine
- labeled and unlabeled data
- classification accuracy
- training set
- active learning
- unlabeled samples
- text classification
- decision trees
- pattern recognition
- manifold regularization
- label propagation
- feature selection
- text categorization
- class labels
- labeled instances
- learning algorithm
- malignant melanoma
- skin cancer
- computer aided
- feature space
- support vector
- training samples
- pairwise
- support vector machine
- community detection
- learning tasks
- model selection
- multi view
- text mining