Classes Matter: A Fine-Grained Adversarial Approach to Cross-Domain Semantic Segmentation.
Haoran WangTong ShenWei ZhangLing-Yu DuanTao MeiPublished in: ECCV (14) (2020)
Keyphrases
- fine grained
- cross domain
- semantic segmentation
- coarse grained
- object classes
- knowledge transfer
- superpixels
- text categorization
- transfer learning
- weakly supervised
- scene classification
- object class
- access control
- conditional random fields
- object categories
- biologically inspired
- information retrieval
- image understanding
- domain specific
- target domain
- image features
- active learning
- training data
- learning algorithm