Why to Combine Reconstructive and Discriminative Information for Incremental Subspace Learning

In the paper we propose a novel method for incremental visual learning by combining reconstructive and discriminative subspace methods. This is achieved by embedding LDA learning and classification into the incremental PCA framework. The combined subspace consists of a truncated PCA subspace and a few additional basis vectors that encompass the discriminative information, which would be lost by the discarded principal vectors. As such it contains both sufficient reconstructive information to enable incremental learning, and the previously extracted discriminative information to enable efficient classification as well. We demonstrate that we are able to efficiently update the current model with new instances of the already learned classes as well as to introduce new classes.