Learning to Transfer Under Unknown Noisy Environments: An Universal Weakly-Supervised Domain Adaptation Method.
Xuan LiuYing HuangShichang HeJiangjin YinXinning ChenShigeng ZhangPublished in: ICME (2021)
Keyphrases
- weakly supervised
- domain adaptation
- prior knowledge
- test data
- target domain
- learning algorithm
- transfer learning
- pairwise
- similarity measure
- object detectors
- pattern recognition
- support vector machine
- semi supervised
- training samples
- cross domain
- unsupervised learning
- superpixels
- learning tasks
- supervised learning
- object recognition
- training data
- feature selection