More Classifiers, Less Forgetting: A Generic Multi-classifier Paradigm for Incremental Learning.
Yu LiuSarah ParisotGregory G. SlabaughXu JiaAles LeonardisTinne TuytelaarsPublished in: ECCV (26) (2020)
Keyphrases
- incremental learning
- unlabeled samples
- fuzzy artmap
- linear classifiers
- individual classifiers
- training data
- multiple classifiers
- classifier combination
- classifier systems
- classifier training
- svm classifier
- probabilistic classifiers
- support vector
- supervised learning
- classification rate
- training set
- class labels
- classification method
- decision trees
- training examples
- training samples
- nearest neighbor classifier
- decision boundary
- binary classifiers
- feature set
- classification algorithm
- ensemble classifier
- combining classifiers
- classifier ensemble
- semi supervised
- discriminative classifiers
- incremental learning algorithm
- multiple classifier systems
- decision tree classifiers
- feature selection
- learning classifier systems
- classification process
- accurate classifiers
- highest accuracy
- ensemble learning
- labeled training data
- learning algorithm
- machine learning
- batch learning
- labeled and unlabeled data
- test set
- multi class
- support vector machine
- naive bayes
- hyperplane
- text classifiers
- classification accuracy
- combining multiple
- reinforcement learning
- training process
- feature vectors
- support vector machine svm
- weak learners
- semi supervised learning
- text classification