Abstract. Canonical correlation analysis (CCA) is a popular method that has been extensively used in feature learning. In nature, the objective function of CCA is equivalent to minimizing the distance… Click to show full abstract
Abstract. Canonical correlation analysis (CCA) is a popular method that has been extensively used in feature learning. In nature, the objective function of CCA is equivalent to minimizing the distance of the paired data, and L2-norm is used as the distance metric. We know that L2-norm-based objective function will emphasize the large distance pairs and de-emphasizes the small distance pairs. To alleviate the aforementioned problems of CCA, we propose an approach named CCA based on L1-norm minimization (CCA-L1) for feature learning. To optimize the objective function, we develop an algorithm that can get a global optimized value. To maintain the distribution and the nonlinear characteristic respectively, we proposed two extensions of CCA-L1. Further, all of the aforementioned three proposed algorithms are extended to deal with multifeature data. The experimental results on an artificial dataset, real-world crop leaf disease dataset, ORL face dataset, and PIE face dataset show that our methods outperform traditional CCA and its variants.
               
Click one of the above tabs to view related content.