Active Learning for Patch-Based Digital Pathology Using Convolutional Neural Networks to Reduce Annotation Costs.
Jacob CarseStephen J. McKennaPublished in: ECDP (2019)
Keyphrases
- active learning
- convolutional neural networks
- convolutional network
- annotation effort
- learning algorithm
- learning strategies
- cost sensitive learning
- maintenance cost
- random sampling
- supervised learning
- semi supervised
- cost sensitive
- active learning strategies
- data sets
- information goods
- relevance feedback
- training set
- training data
- pool based active learning
- training examples
- batch mode
- image super resolution
- labeled data
- visual features
- dynamic programming
- feature extraction
- machine learning