An Optimal Transformation for Discriminant and Principal Component Analysis
IEEE Transactions on Pattern Analysis and Machine Intelligence
Discriminant Adaptive Nearest Neighbor Classification
IEEE Transactions on Pattern Analysis and Machine Intelligence
Locally Adaptive Metric Nearest-Neighbor Classification
IEEE Transactions on Pattern Analysis and Machine Intelligence
Adaptive Kernel Metric Nearest Neighbor Classification
ICPR '02 Proceedings of the 16 th International Conference on Pattern Recognition (ICPR'02) Volume 3 - Volume 3
Pattern Classification (2nd Edition)
Pattern Classification (2nd Edition)
Optimal kernel selection in Kernel Fisher discriminant analysis
ICML '06 Proceedings of the 23rd international conference on Machine learning
Local Fisher discriminant analysis for supervised dimensionality reduction
ICML '06 Proceedings of the 23rd international conference on Machine learning
Dimensionality Reduction of Multimodal Labeled Data by Local Fisher Discriminant Analysis
The Journal of Machine Learning Research
High Reliable Multi-View Semi-Supervised Learning with Extremely Sparse Labeled Data
HIS '08 Proceedings of the 2008 8th International Conference on Hybrid Intelligent Systems
Semantic Features for Multi-view Semi-supervised and Active Learning of Text Classification
ICDMW '08 Proceedings of the 2008 IEEE International Conference on Data Mining Workshops
An efficient algorithm for local distance metric learning
AAAI'06 Proceedings of the 21st national conference on Artificial intelligence - Volume 1
Large margin nearest neighbor classifiers
IEEE Transactions on Neural Networks
ISNN'11 Proceedings of the 8th international conference on Advances in neural networks - Volume Part III
Hi-index | 0.01 |
Fisher discriminant analysis (FDA) has exhibited its great power to improve the performance in classification and dimensionality reduction tasks. Objects in the real world often have more than one natural feature set and therefore they often can be described by more than one views. However, traditional FDA addresses all problems with a single view. In this paper we propose multi-view FDA (MFDA) which combines traditional FDA with multi-view learning. In order to improve the performance of MFDA for multi-class case, we further propose hierarchical MFDA which combines MFDA with hierarchical metric learning. Experiments are performed on many artificial and real-world data sets. Comparisons with the single-view FDA show the effectiveness of the proposed method.