Uncertainty-Aware Consistency Regularization for Cross-Domain Semantic Segmentation.
Qianyu ZhouZhengyang FengGuangliang ChengXin TanJianping ShiLizhuang MaPublished in: CoRR (2020)
Keyphrases
- cross domain
- semantic segmentation
- conditional random fields
- superpixels
- weakly supervised
- knowledge transfer
- text categorization
- scene classification
- object categories
- transfer learning
- image understanding
- graphical models
- object classes
- multi label
- data sets
- natural images
- image classification
- markov random field
- e government
- prior knowledge
- computer vision
- information retrieval