Generating Accurate Pseudo-Labels in Semi-Supervised Learning and Avoiding Overconfident Predictions via Hermite Polynomial Activations.
Vishnu Suresh LokhandeSongwong TasneeyapantAbhay VenkateshSathya N. RaviVikas SinghPublished in: CVPR (2020)
Keyphrases
- semi supervised learning
- label propagation
- semi supervised
- unlabeled data
- labeled data
- training data
- labeled examples
- multi label classification
- unlabeled examples
- multi instance learning
- partially labeled
- active learning
- unlabeled samples
- unsupervised learning
- supervised learning
- class labels
- co training
- semi supervised classification
- learning models
- machine learning
- manifold regularization
- unlabeled instances
- supervised classifiers
- labeled samples
- transfer learning
- pairwise
- text categorization
- training set
- training examples
- pairwise constraints
- multiple instance learning
- semi supervised learning algorithms
- labeled instances
- data sets
- graph based semi supervised learning
- multi instance
- labeled and unlabeled data
- label information
- domain adaptation
- multi label
- probabilistic model
- feature selection
- data mining
- neural network