Learning representations for object classification using multi-stage optimal component analysis

Learning data representations is a fundamental challenge in modeling neural processes and plays an important role in applications such as object recognition. In multi-stage Optimal Component Analysis (OCA), we first hierarchically project the data onto several low dimensional subspaces using standard techniques, then OCA learning is performed hierarchically from the lowest to the highest levels to learn a subspace that is optimal for data discrimination based on the Knearest neighbor classifier. Therefore multi-stage OCA estimates an optimal low-dimensional representation for modeling. One of the main advantages of multi-stage OCA lies in the fact that it greatly improves the computational efficiency of the OCA learning algorithm without sacrificing the recognition performance, thus enhancing its applicability to practical problems. In addition to the nearest neighbor classifier, we illustrate the effectiveness of the learned representations on object classification used in conjunctio...

• Type: Journal
• Year: 2008
• Where: NN
• Authors: Yiming Wu, Xiuwen Liu, Washington Mio
• Keywords: Low Dimensional Subspaces, Multi-stage Optimal Component, Neighbor Classifier, Neural Networks, NN 2008