Large Scale Image Categorization in Sparse Nonparametric Bayesian Representation

There are two main contributions in this paper: (1) A new hierarchical sparse coding algorithm is proposed, which combines hard and soft assignment coding in a fully unsupervised manner for image categorization. Hard coding assigns data into independent cluster globally to enable local dictionary learning to be learned by soft coding. The new coding algorithm is characterized by better fitting of data, more discriminative global clustering, low computational complexity and convergence speed up. (2) We utilize variational inference optimization on large data to solve regularized and optimization problem in the proposed hard soft sparse coding algorithm. Different from other convex optimization algorithm for sparse coding, the proposed algorithm has no limitation or preference on the data with proper prior estimation. In our experiments, we tested MIT 8 scene categories data-set and achieved a 10% improvement on the best existing algorithm with faster convergence rate.