Projects per year
Abstract
Canonical Correlation Analysis (CCA) is widely used for multimodal data analysis and, more recently, for discriminative tasks such as multi-view learning; however, it makes no use of class labels. Recent CCA methods have started to address this weakness but are limited in that they do not simultaneously optimize the CCA projection for discrimination and the CCA projection itself, or they are linear only. We address these deficiencies by simultaneously optimizing a CCA-based and a task objective in an end-to-end manner. Together, these two objectives learn a non-linear CCA projection to a shared latent space that is highly correlated and discriminative. Our method shows a significant improvement over previous state-of-the-art (including deep supervised approaches) for cross-view classification, regularization with a second view, and semi-supervised learning on real data.
Original language | English |
---|---|
DOIs | |
Publication status | Published - 17 Jul 2019 |
Publication series
Name | arXiv |
---|
Keywords
- Machine Learning
Fields of Science and Technology Classification 2012
- 102 Computer Sciences
Projects
- 1 Finished
-
Deep Learning mit persistenter Homologie: Deep Homological Learning
Kwitt, R. (Principal Investigator)
1/08/19 → 30/06/23
Project: Research