A Probabilistic Framework for Discriminative Dictionary Learning

TL;DR

This paper introduces a probabilistic discriminative dictionary learning framework that jointly optimizes a dictionary and classifiers, balancing representation fidelity and classification accuracy, applicable to tasks like digit and face recognition.

Contribution

It presents a novel probabilistic approach to discriminative dictionary learning that integrates diverse classification costs and simplifies optimization using existing sparse coding algorithms.

Findings

Effective on digit classification benchmarks

Improves face recognition accuracy

Flexible with various classification cost functions

Abstract

In this paper, we address the problem of discriminative dictionary learning (DDL), where sparse linear representation and classification are combined in a probabilistic framework. As such, a single discriminative dictionary and linear binary classifiers are learned jointly. By encoding sparse representation and discriminative classification models in a MAP setting, we propose a general optimization framework that allows for a data-driven tradeoff between faithful representation and accurate classification. As opposed to previous work, our learning methodology is capable of incorporating a diverse family of classification cost functions (including those used in popular boosting methods), while avoiding the need for involved optimization techniques. We show that DDL can be solved by a sequence of updates that make use of well-known and well-studied sparse coding and dictionary learning algorithms from the literature. To validate our DDL framework, we apply it to digit classification and face recognition and test it on standard benchmarks.