Combining Semantic Self-Supervision and Self-Training for Domain Adaptation in Semantic Segmentation.
Joshua NiemeijerJörg P. SchäferPublished in: IV Workshops (2021)
Keyphrases
- domain adaptation
- semantic segmentation
- co training
- semi supervised learning
- semi supervised
- weakly supervised
- superpixels
- cross domain
- conditional random fields
- labeled data
- scene classification
- unlabeled data
- multiple sources
- target domain
- active learning
- multi view
- object categories
- transfer learning
- sentiment classification
- text classification
- natural language
- domain specific
- single view
- multiscale
- similarity measure
- multiple views
- machine learning
- image classification
- supervised learning
- small number
- prior knowledge
- training data
- viewpoint
- support vector