Randomized Kernel Multi-view Discriminant Analysis
This work addresses multi-view object recognition challenges in AI and computer vision, but it is incremental as it extends existing methods with kernelization and approximations.
The paper tackles the problem of recognizing objects from multiple heterogeneous views by proposing a kernel version of multi-view discriminant analysis (KMvDA) and using random Fourier features to approximate Gaussian kernels for scalability, achieving competitive performance on popular datasets.
In many artificial intelligence and computer vision systems, the same object can be observed at distinct viewpoints or by diverse sensors, which raises the challenges for recognizing objects from different, even heterogeneous views. Multi-view discriminant analysis (MvDA) is an effective multi-view subspace learning method, which finds a discriminant common subspace by jointly learning multiple view-specific linear projections for object recognition from multiple views, in a non-pairwise way. In this paper, we propose the kernel version of multi-view discriminant analysis, called kernel multi-view discriminant analysis (KMvDA). To overcome the well-known computational bottleneck of kernel methods, we also study the performance of using random Fourier features (RFF) to approximate Gaussian kernels in KMvDA, for large scale learning. Theoretical analysis on stability of this approximation is developed. We also conduct experiments on several popular multi-view datasets to illustrate the effectiveness of our proposed strategy.