Foreground-Aware Stylization and Consensus Pseudo-Labeling for Domain Adaptation of First-Person Hand Segmentation.
Takehiko OhkawaTakuma YagiAtsushi HashimotoYoshitaka UshikuYoichi SatoPublished in: IEEE Access (2021)
Keyphrases
- domain adaptation
- image segmentation
- cross domain
- foreground and background
- background subtraction
- semi supervised
- labeled data
- active learning
- multiple sources
- semi supervised learning
- test data
- sentiment classification
- data sets
- unlabeled data
- transfer learning
- unsupervised learning
- covariate shift
- manifold alignment
- document classification
- co training
- object segmentation
- sentiment analysis
- text classification
- face recognition
- feature selection