Attract, Perturb, and Explore: Learning a Feature Alignment Network for Semi-supervised Domain Adaptation.
Taekyung KimChangick KimPublished in: ECCV (14) (2020)
Keyphrases
- domain adaptation
- semi supervised
- labeled data
- active learning
- learning algorithm
- semi supervised learning
- unlabeled data
- reinforcement learning
- learning process
- supervised learning
- co training
- covariate shift
- manifold alignment
- labeled and unlabeled data
- multiple sources
- training data
- knowledge transfer
- natural language