From Shallow to Deep: Exploiting Feature-Based Classifiers for Domain Adaptation in Semantic Segmentation.
Alex MatskevychAdrian WolnyConstantin PapeAnna KreshukPublished in: Frontiers Comput. Sci. (2022)
Keyphrases
- domain adaptation
- semantic segmentation
- co training
- training data
- conditional random fields
- labeled data
- test data
- superpixels
- semi supervised
- multiple sources
- cross domain
- semi supervised learning
- weakly supervised
- labeled training data
- target domain
- decision trees
- information extraction
- support vector
- transfer learning
- machine learning algorithms
- object categories
- training samples
- unlabeled data
- training set
- feature selection
- training examples
- natural language processing
- sentiment classification
- feature set
- image features
- feature space
- question answering
- computer vision
- object classes
- generative model
- supervised learning
- pairwise