Classification of Degraded Traffic Signs Using Flexible Mixture Model and Transfer Learning.
Abdul MannanKashif Javed Atta-ur-RehmanHaroon A. BabriSerosh Karim NoonPublished in: IEEE Access (2019)
Keyphrases
- mixture model
- transfer learning
- traffic signs
- text classification
- machine learning
- em algorithm
- model selection
- unsupervised learning
- machine learning algorithms
- generative model
- learning tasks
- pattern recognition
- gaussian mixture model
- language model
- reinforcement learning
- cross domain
- training samples
- expectation maximization
- probabilistic model
- decision trees
- supervised learning
- transfer knowledge
- label information
- automatic recognition
- collaborative filtering
- learning algorithm
- multi task
- training set
- semi supervised learning
- labeled data
- active learning
- feature vectors
- computer vision
- unlabeled samples
- pairwise
- object recognition
- class labels
- support vector
- data mining
- support vector machine
- labeled and unlabeled data
- information retrieval
- multi class