Learning to Attack Real-World Models for Person Re-identification via Virtual-Guided Meta-Learning.
Fengxiang YangZhun ZhongHong LiuZheng WangZhiming LuoShaozi LiNicu SebeShin'ichi SatohPublished in: AAAI (2021)
Keyphrases
- meta learning
- real world
- learning tasks
- inductive learning
- person re identification
- data sets
- model selection
- learning process
- learning algorithm
- prior knowledge
- machine learning
- reinforcement learning
- object recognition
- base classifiers
- data mining
- supervised learning
- machine learning algorithms
- knowledge base
- decision trees
- active learning