Toward Learning Human-aligned Cross-domain Robust Models by Countering Misaligned Features.
Haohan WangZeyi HuangHanlin ZhangEric Po XingPublished in: CoRR (2021)
Keyphrases
- cross domain
- prior knowledge
- learned models
- learning process
- learning algorithm
- knowledge transfer
- domain adaptation
- feature extraction
- reinforcement learning
- model selection
- knowledge sharing
- domain specific
- data sets
- neural network
- learning tasks
- information sharing
- machine learning
- feature vectors
- support vector
- case study