Aligning Infinite-Dimensional Covariance Matrices in Reproducing Kernel Hilbert Spaces for Domain Adaptation.
Zhen ZhangMianzhi WangYan HuangArye NehoraiPublished in: CVPR (2018)
Keyphrases
- reproducing kernel hilbert space
- domain adaptation
- infinite dimensional
- finite dimensional
- covariance matrix
- cross domain
- multiple sources
- principal component analysis
- labeled data
- semi supervised
- semi supervised learning
- sample size
- sentiment classification
- transfer learning
- gaussian mixture model
- vector space
- target domain
- unlabeled data
- test data
- learning tasks
- co training
- k nearest neighbor