Learning Semantic Patterns with Discriminant Localized Binary Projections

In this paper, we present a novel approach to learning semantic localized patterns with binary projections in a su-pervised manner. The pursuit of these binary projections is reformulated into a problem of feature clustering, which optimizes the separability of different classes by taking the members within each cluster as the nonzero entries of a pro-jection vector. An efficient greedy procedure is proposed to incrementally combine the sub-clusters by ensuring the cardinality constraints of the projections and the increase of the objective function. Compared with other algorithms for sparse representations, our proposed algorithm, referred to as Discriminant Localized Binary Projections (dlb), has the following characteristics: 1) dlb is supervised, hence is much more effective than other unsupervised sparse al-gorithms like Non-negative Matrix Factorization (NMF) in terms of classification power; 2) similar to NMF, dlb can de-rive spatially localized sparse bases; furthermore, the spar-sity of dlb is controllable, and an interesting result is that the bases have explicit semantics in human perception, like eyes and mouth; and 3) classification with dlb is extremely effi-cient, and only addition operations are required for dimen-sionality reduction. Extensive experimental results show significant improvements of dlb in sparsity and face recog-nition accuracy in comparison to the state-of-the-art algo-rithms for dimensionality reduction and sparse representa-tions. 1