SHIFT: A Synthetic Driving Dataset for Continuous Multi-Task Domain Adaptation.
Tao SunMattia SegùJanis PostelsYuxuan WangLuc Van GoolBernt SchieleFederico TombariFisher YuPublished in: CoRR (2022)
Keyphrases
- domain adaptation
- multi task
- transfer learning
- multi task learning
- learning tasks
- transfer knowledge
- target domain
- cross domain
- multiple sources
- labeled data
- feature selection
- metric learning
- multi class
- reinforcement learning
- learning problems
- semi supervised
- knowledge transfer
- text categorization
- machine learning
- test data
- unlabeled data
- semi supervised learning
- training data
- document classification
- feature set
- collaborative filtering
- sentiment classification
- databases
- test set
- text classification
- active learning
- feature space
- co training
- information retrieval