ScatSimCLR: self-supervised contrastive learning with pretext task regularization for small-scale datasets.
Vitaliy KinakhOlga TaranSvyatoslav VoloshynovskiyPublished in: ICCVW (2021)
Keyphrases
- small scale
- learning systems
- reinforcement learning
- learning process
- active learning
- learning algorithm
- knowledge acquisition
- empirical studies
- inductive learning
- learning tasks
- prior knowledge
- online learning
- learning scenarios
- multi task learning
- incremental learning
- background knowledge
- learning experience
- case study