Discriminative models for robust image classification

TL;DR

This paper develops discriminative graphical models that leverage multiple image representations to improve robustness in image classification, especially under limited training data and noisy conditions.

Contribution

It introduces a discriminative tree-based feature fusion framework that explicitly learns conditional correlations among multiple image projections.

Findings

Robustness to training insufficiency demonstrated

Effective feature fusion via discriminative graphical models

Improved classification accuracy under noise and distortions

Abstract

A variety of real-world tasks involve the classification of images into pre-determined categories. Designing image classification algorithms that exhibit robustness to acquisition noise and image distortions, particularly when the available training data are insufficient to learn accurate models, is a significant challenge. This dissertation explores the development of discriminative models for robust image classification that exploit underlying signal structure, via probabilistic graphical models and sparse signal representations. Probabilistic graphical models are widely used in many applications to approximate high-dimensional data in a reduced complexity set-up. Learning graphical structures to approximate probability distributions is an area of active research. Recent work has focused on learning graphs in a discriminative manner with the goal of minimizing classification error. In the first part of the dissertation, we develop a discriminative learning framework that exploits the complementary yet correlated information offered by multiple representations (or projections) of a given signal/image. Specifically, we propose a discriminative tree-based scheme for feature fusion by explicitly learning the conditional correlations among such multiple projections in an iterative manner. Experiments reveal the robustness of the resulting graphical model classifier to training insufficiency.