Class-specific mid-level feature learning with the Discriminative Group-wise Beta-Bernoulli process restricted Boltzmann machines

• We propose an weakly-supervised approach to learn class-specific mid-level features.
• We introduce new bias vectors that encode discriminative sparsity properties between classes.
• Bayesian generative model’s priors are newly defined with proposed bias vectors.
• We impose class-specific sparsity on the restricted Boltzmann machine with newly-defined priors.
• Our method achieved better results than did related methods for different two image classification tasks.

In this paper, we propose a Discriminative Group-wise Beta-Bernoulli process restricted Boltzmann machine (DG-BBP RBM), an approach to learn class-specific mid-level features based on the Beta-Bernoulli process restricted Boltzmann machine (BBP RBM), which imposes class-specific sparsity that has discriminative characteristics across different classes to eliminate redundancy among extracted features. With this method, we learn mid-level features that are characteristic of each class and that are shared rarely or not at all with other classes (i.e., are discriminative of that class). In experiments on image classification tasks, our DG-BBP RBM showed much better results than did BBP RBM and related methods and could capture semantic attributes that can be used to discriminate between classes.